Computer audition aims to enable machines to understand, process and generate human-audible signals, including speech, environmental sound and music. The field is now evolving beyond traditional paradigms to fully leverage the capabilities of foundation models, towards more comprehensive understanding, more natural generation and more human-like interaction. Audio, as a modality rich in semantic, emotional and contextual cues, has a vital role in achieving naturalistic and embodied machine intelligence. This Review provides a comprehensive review of recent progress in integrating audio into large language models, with a focus on four key areas: audio comprehension, audio generation, speech-based interaction and audio–visual understanding. We analyse how large language models are reshaping audio perception and reasoning, enabling systems to understand sound at a deeper semantic level, generate expressive audio outputs and engage in human-like spoken interaction. Furthermore, we explore how the fusion of audio and visual modalities enhances situational awareness and cross-modal reasoning, pushing the boundaries of multimodal intelligence. This Review not only synthesizes existing research but also identifies critical challenges and future directions for building general auditory intelligence capable of perceiving, understanding and interacting through sound as naturally as humans do. Wang et al. summarize advances in machine listening and speaking, speech-based interaction, and audio–visual understanding.

In the era of large language models (LLMs) and artificial general intelligence (AGI), computer audition must evolve beyond traditional paradigms to fully leverage the capabilities of foundation models, towards more comprehensive understanding, more natural generation and more human-like interaction. Audio, as a modality rich in semantic, emotional, and contextual cues, plays a vital role in achieving naturalistic and embodied machine intelligence. This survey provides a comprehensive review of recent progress in integrating audio into LLMs, with a focus on four key areas: audio comprehension, audio generation, speech-based interaction, and audio-visual understanding. We analyze how LLMs are reshaping audio perception and reasoning, enabling systems to understand sound at a deeper semantic level, generate expressive audio outputs, and engage in human-like spoken interaction. Furthermore, we explore how the fusion of audio and visual modalities enhances situational awareness and cross-modal reasoning, pushing the boundaries of multimodal intelligence. This survey not only synthesizes existing research but also identifies critical challenges and future directions for building audio-native AGI systems capable of perceiving, understanding, and interacting through sound as naturally as humans do.

We investigate massive end-to-end automatic speech recognition (ASR) models with efficiency improvements achieved by time reduction. The encoders of our models use the neural architecture of Google's universal speech model (USM), with additional funnel pooling layers to significantly reduce the frame rate and speed up training and inference. We also explore a few practical methods to mitigate potential accuracy loss due to time reduction, while enjoying most efficiency gain. Our methods are demonstrated to work with both Connectionist Temporal Classification (CTC) and RNN-Transducer (RNN-T), with up to 2B model parameters, and over two domains. For a large-scale voice search recognition task, we perform extensive studies on vocabulary size, time reduction strategy, and its generalization performance on long-form test sets, and show that a 900M RNN-T is very tolerant to severe time reduction, with as low encoder output frame rate as 640ms. We also provide ablation studies on the Librispeech benchmark for important training hyperparameters and architecture designs, in training 600M RNN-T models at the frame rate of 160ms.

The subjective perception of emotion leads to inconsistent labels from human annotators. Typically, utterances lacking majority-agreed labels are excluded when training an emotion classifier, which cause problems when encountering ambiguous emotional expressions during testing. This paper investigates three methods to handle ambiguous emotion. First, we show that incorporating utterances without majority-agreed labels as an additional class in the classifier reduces the classification performance of the other emotion classes. Then, we propose detecting utterances with ambiguous emotions as out-of-domain samples by quantifying the uncertainty in emotion classification using evidential deep learning. This approach retains the classification accuracy while effectively detects ambiguous emotion expressions. Furthermore, to obtain fine-grained distinctions among ambiguous emotions, we propose representing emotion as a distribution instead of a single class label. The task is thus re-framed from classification to distribution estimation where every individual annotation is taken into account, not just the majority opinion. The evidential uncertainty measure is extended to quantify the uncertainty in emotion distribution estimation. Experimental results on the IEMOCAP and CREMA-D datasets demonstrate the superior capability of the proposed method in terms of majority class prediction, emotion distribution estimation, and uncertainty estimation.

The accuracy of end-to-end (E2E) automatic speech recognition (ASR) models continues to improve as they are scaled to larger sizes, with some now reaching billions of parameters. Widespread deployment and adoption of these models, however, requires computationally efficient strategies for decoding. In the present work, we study one such strategy: applying multiple frame reduction layers in the encoder to compress encoder outputs into a small number of output frames. While similar techniques have been investigated in previous work, we achieve dramatically more reduction than has previously been demonstrated through the use of multiple funnel reduction layers. Through ablations, we study the impact of various architectural choices in the encoder to identify the most effective strategies. We demonstrate that we can generate one encoder output frame for every 2.56 sec of input speech, without significantly affecting word error rate on a large-scale voice search task, while improving encoder and decoder latencies by 48% and 92% respectively, relative to a strong but computationally expensive baseline.

The end-to-end ASR model is often desired in the streaming multilingual scenario since it is easier to deploy and can benefit from pre-trained speech models such as powerful foundation models. Meanwhile, the heterogeneous nature and imbalanced data abundance of different languages may cause performance degradation, leading to asynchronous peak performance for different languages during training, especially on tail ones. Sometimes even the data itself may become unavailable as a result of the enhanced privacy protection. Existing work tends to significantly increase the model size or learn language-specific decoders to accommodate each language separately. In this study, we explore simple yet effective Language-Dependent Adapter (LDA) finetuning under a cascaded Conformer transducer framework enhanced by teacher pseudolabeling for tail languages in the streaming multilingual ASR. The adapter only accounts for 0.4% of the full model per language. It is plugged into the frozen foundation model and is the only trainable module during the finetuning process with noisy student training. The final model merges the adapter parameters from different checkpoints for different languages. The model performance is validated on a challenging multilingual dictation dataset, which includes 39 tail languages across Latin, Greek, Arabic, etc. Our proposed method brings 12.2% word error rate reduction on average and up to 37.5% on a single locale. Furthermore, we show that our parameter-efficient LDA can match the quality of the full model finetuning, thus greatly alleviating the asynchronous peak performance issue.

Contextual biasing refers to the problem of biasing the automatic speech recognition (ASR) systems towards rare entities that are relevant to the specific user or application scenarios. We propose algorithms for contextual biasing based on the Knuth-Morris-Pratt algorithm for pattern matching. During beam search, we boost the score of a token extension if it extends matching into a set of biasing phrases. Our method simulates the classical approaches often implemented in the weighted finite state transducer (WFST) framework, but avoids the FST language altogether, with careful considerations on memory footprint and efficiency on tensor processing units (TPUs) by vectorization. Without introducing additional model parameters, our method achieves significant word error rate (WER) reductions on biasing test sets by itself, and yields further performance gain when combined with a model-based biasing method.

In this report, we introduce the Gemini 1.5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over fine-grained information from millions of tokens of context, including multiple long documents and hours of video and audio. The family includes two new models: (1) an updated Gemini 1.5 Pro, which exceeds the February version on the great majority of capabilities and benchmarks; (2) Gemini 1.5 Flash, a more lightweight variant designed for efficiency with minimal regression in quality. Gemini 1.5 models achieve near-perfect recall on long-context retrieval tasks across modalities, improve the state-of-the-art in long-document QA, long-video QA and long-context ASR, and match or surpass Gemini 1.0 Ultra's state-of-the-art performance across a broad set of benchmarks. Studying the limits of Gemini 1.5's long-context ability, we find continued improvement in next-token prediction and near-perfect retrieval (>99 as Claude 3.0 (200k) and GPT-4 Turbo (128k). Finally, we highlight real-world use cases, such as Gemini 1.5 collaborating with professionals on completing their tasks achieving 26 to 75 categories, as well as surprising new capabilities of large language models at the frontier; when given a grammar manual for Kalamang, a language with fewer than 200 speakers worldwide, the model learns to translate English to Kalamang at a similar level to a person who learned from the same content.

In the era of large models, the autoregressive nature of decoding often results in latency serving as a significant bottleneck. We propose a non-autoregressive LM-fused ASR system that effectively leverages the parallelization capabilities of accelerator hardware. Our approach combines the Universal Speech Model (USM) and the PaLM 2 language model in per-segment scoring mode, achieving an average relative WER improvement across all languages of 10.8% on FLEURS and 3.6% on YouTube captioning. Furthermore, our comprehensive ablation study analyzes key parameters such as LLM size, context length, vocabulary size, fusion methodology. For instance, we explore the impact of LLM size ranging from 128M to 340B parameters on ASR performance. This study provides valuable insights into the factors influencing the effectiveness of practical large-scale LM-fused speech recognition systems.

A recent paradigm shift in artificial intelligence has seen the rise of foundation models, such as the large language models and the universal speech models. With billions of model parameters and trained with a wide range of data, these foundation models are expected to have a better generalization to different downstream tasks. Efficient adaptation is the key to leveraging these foundation models in a new task or domain. In this paper, we compare several popular parameter-efficient tuning methods, such as vector adaptation, residual adapters, low-rank adapter (LoRA) and prompt-tuning, for automatic speech recognition (ASR) domain adaptation. We use the connectionist temporal classification (CTC) model with Conformer encoder and fused it with a universal language model. We study the effect of adapting either or both of the Conformer encoder and the universal language model. We carry out extensive experiments to study these methods under different hyper-parameter settings and the effect of combining some of these methods. We find that combining vector adaptation and residual adapters with increasing bottleneck dimension achieved the best performance.

In the last decade of automatic speech recognition (ASR) research, the introduction of deep learning has brought considerable reductions in word error rate of more than 50% relative, compared to modeling without deep learning. In the wake of this transition, a number of all-neural ASR architectures have been introduced. These so-called end-to-end (E2E) models provide highly integrated, completely neural ASR models, which rely strongly on general machine learning knowledge, learn more consistently from data, with lower dependence on ASR domain-specific experience. The success and enthusiastic adoption of deep learning, accompanied by more generic model architectures has led to E2E models now becoming the prominent ASR approach. The goal of this survey is to provide a taxonomy of E2E ASR models and corresponding improvements, and to discuss their properties and their relationship to classical hidden Markov model (HMM) based ASR architectures. All relevant aspects of E2E ASR are covered in this work: modeling, training, decoding, and external language model integration, discussions of performance and deployment opportunities, as well as an outlook into potential future developments.

Online speech recognition, where the model only accesses context to the left, is an important and challenging use case for ASR systems. In this work, we investigate augmenting neural encoders for online ASR by incorporating structured state-space sequence models (S4), a family of models that provide a parameter-efficient way of accessing arbitrarily long left context. We performed systematic ablation studies to compare variants of S4 models and propose two novel approaches that combine them with convolutions. We found that the most effective design is to stack a small S4 using real-valued recurrent weights with a local convolution, allowing them to work complementarily. Our best model achieves WERs of 4.01%/8.53% on test sets from Librispeech, outperforming Conformers with extensively tuned convolution.

Neural contextual biasing effectively improves automatic speech recognition (ASR) for crucial phrases within a speaker's context, particularly those that are infrequent in the training data. This work proposes contextual text injection (CTI) to enhance contextual ASR. CTI leverages not only the paired speech-text data, but also a much larger corpus of unpaired text to optimize the ASR model and its biasing component. Unpaired text is converted into speech-like representations and used to guide the model's attention towards relevant bias phrases. Moreover, we introduce a contextual text-injected (CTI) minimum word error rate (MWER) training, which minimizes the expected WER caused by contextual biasing when unpaired text is injected into the model. Experiments show that CTI with 100 billion text sentences can achieve up to 43.3% relative WER reduction from a strong neural biasing model. CTI-MWER provides a further relative improvement of 23.5%.

Automatic speech recognition (ASR) systems have been shown to have large quality disparities between the language varieties they are intended or expected to recognize. One way to mitigate this is to train or fine-tune models with more representative datasets. But this approach can be hindered by limited in-domain data for training and evaluation. We propose a new way to improve the robustness of a US English short-form speech recognizer using a small amount of out-of-domain (long-form) African American English (AAE) data. We use CORAAL, YouTube and Mozilla Common Voice to train an audio classifier to approximately output whether an utterance is AAE or some other variety including Mainstream American English (MAE). By combining the classifier output with coarse geographic information, we can select a subset of utterances from a large corpus of untranscribed short-form queries for semi-supervised learning at scale. Fine-tuning on this data results in a 38.5% relative word error rate disparity reduction between AAE and MAE without reducing MAE quality.

End-to-end automatic speech recognition (ASR) models have seen revolutionary quality gains with the recent development of large-scale universal speech models (USM). However, deploying these massive USMs is extremely expensive due to the enormous memory usage and computational cost. Therefore, model compression is an important research topic to fit USM-based ASR under budget in real-world scenarios. In this study, we propose a USM fine-tuning approach for ASR, with a low-bit quantization and N:M structured sparsity aware paradigm on the model weights, reducing the model complexity from parameter precision and matrix topology perspectives. We conducted extensive experiments with a 2-billion parameter USM on a large-scale voice search dataset to evaluate our proposed method. A series of ablation studies validate the effectiveness of up to int4 quantization and 2:4 sparsity. However, a single compression technique fails to recover the performance well under extreme setups including int2 quantization and 1:4 sparsity. By contrast, our proposed method can compress the model to have 9.4% of the size, at the cost of only 7.3% relative word error rate (WER) regressions. We also provided in-depth analyses on the results and discussions on the limitations and potential solutions, which would be valuable for future studies.

Parameter efficient adaptation methods have become a key mechanism to train large pre-trained models for downstream tasks. However, their per-task parameter overhead is considered still high when the number of downstream tasks to adapt for is large. We introduce an adapter module that has a better efficiency in large scale multi-task adaptation scenario. Our adapter is hierarchical in terms of how the adapter parameters are allocated. The adapter consists of a single shared controller network and multiple task-level adapter heads to reduce the per-task parameter overhead without performance regression on downstream tasks. The adapter is also recurrent so the entire adapter parameters are reused across different layers of the pre-trained model. Our Hierarchical Recurrent Adapter (HRA) outperforms the previous adapter-based approaches as well as full model fine-tuning baseline in both single and multi-task adaptation settings when evaluated on automatic speech recognition tasks.

ASR models often suffer from a long-form deletion problem where the model predicts sequential blanks instead of words when transcribing a lengthy audio (in the order of minutes or hours). From the perspective of a user or downstream system consuming the ASR results, this behavior can be perceived as the model "being stuck", and potentially make the product hard to use. One of the culprits for long-form deletion is training-test data mismatch, which can happen even when the model is trained on diverse and large-scale data collected from multiple application domains. In this work, we introduce a novel technique to simultaneously model different groups of speakers in the audio along with the standard transcript tokens. Speakers are grouped as primary and non-primary, which connects the application domains and significantly alleviates the long-form deletion problem. This improved model neither needs any additional training data nor incurs additional training or inference cost.

End-to-end models with large capacity have significantly improved multilingual automatic speech recognition, but their computation cost poses challenges for on-device applications. We propose a streaming truly multilingual Conformer incorporating mixture-of-expert (MoE) layers that learn to only activate a subset of parameters in training and inference. The MoE layer consists of a softmax gate which chooses the best two experts among many in forward propagation. The proposed MoE layer offers efficient inference by activating a fixed number of parameters as the number of experts increases. We evaluate the proposed model on a set of 12 languages, and achieve an average 11.9% relative improvement in WER over the baseline. Compared to an adapter model using ground truth information, our MoE model achieves similar WER and activates similar number of parameters but without any language information. We further show around 3% relative WER improvement by multilingual shallow fusion.

In this paper, we explore various frame rate reduction schemes on the two-pass cascaded encoder model to improve its efficiency without scarifying the transcription quality. We conduct extensive studies on frame rate reduction strategies, left and right context window length, trade-offs in quality, latency, computation and power consumption, and performance in short-and long-form datasets. With the proposed schemes, we can lower the 2nd pass frame rate to $120 \mathrm{~ms}$, half of the 1st pass’s. This achieves $20 \%$ RTF reduction / $13 \%$ power saving / $19 \%$ lower final latency, without impact on the word-error-rate nor partial results’ latency. If allowing partial latency increase, we can further reduce the frame rate to $180 \mathrm{~ms}$ or even $240 \mathrm{~ms}$ from the 1st pass, and obtain $45 \%$ RTF / 35% power savings, with a similar or even better (on the short-form testset) recognition accuracy.

In end-to-end (E2E) speech recognition models, a representational tight-coupling inevitably emerges between the encoder and the decoder. We build upon recent work that has begun to explore building encoders with modular encoded representations, such that encoders and decoders from different models can be stitched together in a zero-shot manner without further fine-tuning. While previous research only addresses full-context speech models, we explore the problem in a streaming setting as well. Our framework builds on top of existing encoded representations, converting them to modular features, dubbed as Lego-Features, without modifying the pre-trained model. The features remain interchangeable when the model is retrained with distinct initializations. Though sparse, we show that the Lego-Features are powerful when tested with RNN-T or LAS decoders, maintaining high-quality downstream performance. They are also rich enough to represent the first-pass prediction during two-pass deliberation. In this scenario, they outperform the N-best hypotheses, since they do not need to be supplemented with acoustic features to deliver the best results. Moreover, generating the Lego-Features does not require beam search or auto-regressive computation. Overall, they present a modular, powerful and cheap alternative to the standard encoder output, as well as the N-best hypotheses.