CHILDES is a large-scale child speech corpus containing long-form recordings of naturalistic child-adult interactions, making it a valuable resource for studying child speech and language development. However, utterance-level timestamps provided in this corpus are often noisy, incomplete, or misaligned with the audio. As a result, utterances cannot always be reliably localized within long recordings, which limits the direct use of these data for training and evaluating speech models. In this work, we propose BEACON (Boundary Estimation via Alignment CONsensus), an ensemble timestamp-curation framework that refines utterance-level timestamps by aggregating knowledge from multiple off-the-shelf ASR models. Specifically, each model's word-level timestamp predictions are first aligned to provided human transcripts, and the final utterance time boundaries are determined by a consensus voting strategy. The framework is corpus-agnostic and applies to any long-form recording paired with a trusted transcript whose timestamps are unreliable or missing, offering a general recipe for timestamp curation. Leveraging this pipeline, we curate and release a 413-hour general-purpose child-speech dataset with corrected utterance-level timestamps, together with a 283-hour quality-controlled subset for ASR training. Fine-tuning on this subset yields up to an average 19.5

Self-supervised pre-training using unlabeled data is widely used in automatic speech recognition. In this paper, we propose a new self-supervised pre-training approach to dealing with heterogeneous data. Instead of mixing all the data and minimizing the averaged global loss in the conventional way, we impose additional local constraints to ensure that the model optimizes each source of heterogeneous data to its local optimum after K-step gradient descent initialized from the model. We formulate this as a bilevel optimization problem, and use the first-order approximation method to solve the problem. We discuss its connection to model-agnostic meta learning. Experiments are carried out on self-supervised pre-training using multi-domain and multilingual datasets, demonstrating that the proposed approach can significantly improve the adaptivity of the self-supervised pre-trained model for the downstream supervised fine-tuning tasks.

Recent video reasoning models have shown strong results on temporal and multimodal understanding, yet they depend on large-scale supervised data and multi-stage training pipelines, making them costly to train and difficult to adapt to new domains. In this work, we leverage the paradigm of Test-Time Reinforcement Learning on video-language data to allow for adapting a pretrained model to incoming video samples at test-time without explicit labels. The proposed test-time adaptation for video approach (TTA-Vid) combines two components that work simultaneously: (1) a test-time adaptation that performs step-by-step reasoning at inference time on multiple frame subsets. We then use a batch-aware frequency-based reward computed across different frame subsets as pseudo ground truth to update the model. It shows that the resulting model trained on a single batch or even a single sample from a dataset, is able to generalize at test-time to the whole dataset and even across datasets. Because the adaptation occurs entirely at test time, our method requires no ground-truth annotations or dedicated training splits. Additionally, we propose a multi-armed bandit strategy for adaptive frame selection that learns to prioritize informative frames, guided by the same reward formulation. Our evaluation shows that TTA-Vid yields consistent improvements across various video reasoning tasks and is able to outperform current state-of-the-art methods trained on large-scale data. This highlights the potential of test-time reinforcement learning for temporal multimodal understanding.

Recent advances in reasoning models have shown remarkable progress in text-based domains, but transferring those capabilities to multimodal settings, e.g., to allow reasoning over audio-visual data, still remains a challenge, in part because of the limited availability of high-quality reasoning data in targeted multimodal combinations. To address this problem, we introduce AVRT, a novel framework that generates high-quality audio-visual reasoning traces from single-modality teacher models. We generate independent vision- and audio-reasoning traces via models specialized to reason over their respective modalities and merge the resulting traces with an LLM merger model. The resulting multimodal traces are used in a supervised fine-tuning (SFT) cold start to adapt the target model to audio-visual reasoning traces first, before training it in a second reinforcement learning stage on larger-scale data. Evaluated on seven audio-visual and audio benchmarks, our 3B and 7B parameter models achieve state-of-the-art results among models of comparable size including OmniBench and DailyOmni for audio-visual and MMAR for audio-only reasoning, showing that cross-modal training also transfers to single-modality tasks and establishing a new training pipeline for multimodal reasoning models.

Recent advances in speech-aware language models have coupled strong acoustic encoders with large language models, enabling systems that move beyond transcription to produce richer outputs. Among these, word-level timestamp prediction is critical for applications such as captioning, media search, and multimodal synchronization, yet it is often handled by external alignment tools. In this work, we extend an existing speech-aware language model to predict timestamps directly alongside transcripts. We introduce a set of novel lightweight training strategies that improve alignment robustness while preserving recognition quality. Experiments across multiple datasets show that these strategies not only enhance timestamp accuracy, but also yield gains in overall ASR performance. Together, they demonstrate an efficient and unified approach to speech recognition with precise timestamp prediction.

Speech is a rich signal, and labeled audio–text pairs are costly to obtain, making self-supervised learning (SSL) essential for scalable representation learning. A core challenge in speech SSL is generating pseudo-labels that are both informative and efficient: strong labels, such as those used in HuBERT [1], improve downstream performance but rely on external encoders and multi-stage pipelines, while efficient methods like BEST-RQ [2] achieve simplicity at the cost of weaker labels. We propose BiRQ, a bilevel SSL framework that combines the efficiency of BEST-RQ with the refinement benefits of HuBERT-style label enhancement. The key idea is to reuse part of the model itself as a pseudo-label generator: intermediate representations are discretized by a random-projection quantizer to produce enhanced labels, while anchoring labels derived directly from the raw input stabilize training and prevent collapse. Training is formulated as an efficient first-order bilevel optimization problem, solved end-to-end with differentiable Gumbel-softmax selection. This design eliminates the need for external label encoders, reduces memory cost, and enables iterative label refinement in an end-to-end fashion. BiRQ consistently improves over BEST-RQ while maintaining low complexity and computational efficiency. We validate our method on various datasets, including 960-hour LibriSpeech, 150-hour AMI meetings and 5,000-hour YODAS, demonstrating consistent gains over BEST-RQ.

In this paper, we take a step towards jointly modeling automatic speech recognition (STT) and speech synthesis (TTS) in a fully non-autoregressive way. We develop a novel multimodal framework capable of handling the speech and text modalities as input either individually or together. The proposed model can also be trained with unpaired speech or text data owing to its multimodal nature. We further propose an iterative refinement strategy to improve the STT and TTS performance of our model such that the partial hypothesis at the output can be fed back to the input of our model, thus iteratively improving both STT and TTS predictions. We show that our joint model can effectively perform both STT and TTS tasks, outperforming the STT-specific baseline in all tasks and performing competitively with the TTS-specific baseline across a wide range of evaluation metrics.

Granite-speech LLMs are compact and efficient speech language models specifically designed for English ASR and automatic speech translation (AST). The models were trained by modality aligning the 2B and 8B parameter variants of granite-3.3-instruct to speech on publicly available open-source corpora containing audio inputs and text targets consisting of either human transcripts for ASR or automatically generated translations for AST. Comprehensive benchmarking shows that on English ASR, which was our primary focus, they outperform several competitors' models that were trained on orders of magnitude more proprietary data, and they keep pace on English-to-X AST for major European languages, Japanese, and Chinese. The speech-specific components are: a conformer acoustic encoder using block attention and self-conditioning trained with connectionist temporal classification, a windowed query-transformer speech modality adapter used to do temporal downsampling of the acoustic embeddings and map them to the LLM text embedding space, and LoRA adapters to further fine-tune the text LLM. Granite-speech-3.3 operates in two modes: in speech mode, it performs ASR and AST by activating the encoder, projector, and LoRA adapters; in text mode, it calls the underlying granite-3.3-instruct model directly (without LoRA), essentially preserving all the text LLM capabilities and safety. Both models are freely available on HuggingFace (https://huggingface.co/ibm-granite/granite-speech-3.3-2b and https://huggingface.co/ibm-granite/granite-speech-3.3-8b) and can be used for both research and commercial purposes under a permissive Apache 2.0 license.

Conformer CTC-Encoders have consistently delivered state-of-the-art results in the field of Automatic Speech Recognition (ASR); however, their merits for tasks that demand more semantic and paralinguistic information, such as Automatic Speech Understanding (ASU), Speech Emotion Recognition (SER) and Speech Translation (ST), still need further investigation. In this paper, we introduce a Speech Large Language Model (SLLM) system based on a Conformer CTC-Encoder and on the Granite Large Language Model that allowed us to perform several experiments on ASR, SER and ST tasks. These experiments have not only confirmed the strength of Conformer CTC-encoders for ASR, but also, they have shown that the outputs of intermediate Conformer Blocks, of the Conformer CTC-Encoder, carry important information for SER tasks and that the Conformer CTC-Encoder can be efficiently fine-tuned for SER tasks.

The human brain's ability to transform acoustic speech signals into rich linguistic representations has inspired advancements in automatic speech recognition (ASR) systems. While ASR systems now achieve human-level performance under controlled conditions, prior research on their parallels with the brain has been limited by the use of biologically implausible models, narrow feature sets, and comparisons that primarily emphasize predictability of brain activity without fully exploring shared underlying representations. Additionally, studies comparing the brain to text-based language models overlook the acoustic stages of speech processing, an essential part in transforming sound to meaning. Leveraging high-resolution intracranial recordings and a recurrent ASR model, this study bridges these gaps by uncovering a striking correspondence in the hierarchical encoding of linguistic features, from low-level acoustic signals to high-level semantic processing. Specifically, we demonstrate that neural activity in distinct regions of the auditory cortex aligns with representations in corresponding layers of the ASR model and, crucially, that both systems encode similar features at each stage of processing-from acoustic to phonetic, lexical, and semantic information. These findings suggest that both systems, despite their distinct architectures, converge on similar strategies for language processing, providing insight in the optimal computational principles underlying linguistic representation and the shared constraints shaping human and artificial speech processing.

We present MADASR 2.0, a challenge at ASRU 2025 aimed at advancing multilingual and multidialectal automatic speech recognition (ASR) in low-resource Indian languages. Building on the 2023 edition, it introduces a subset of the RESPIN corpus, over 1200 hours of read speech across 8 languages and 33 dialects, with test sets including both read and spontaneous speech. The challenge comprises four tracks varying by training data size and external resource usage, and supports auxiliary tasks like language and dialect identification. We detail the dataset, tasks, baselines, and submissions and analyse trends across tracks and speech styles. Results highlight the continued difficulty of spontaneous ASR, the benefits of multitask and transfer learning, and effective strategies for building dialect-aware ASR systems. MADASR 2.0 offers a standardised benchmark to support future research on inclusive and scalable ASR for linguistically diverse populations.

The need for training multilingual multi-task speech processing (MSP) models that perform both automatic speech recognition and speech-to-text translation is increasingly evident. However, a significant challenge arises from the conflicts among multiple objectives when using a single model. Multi-objective optimization can address this challenge by facilitating the optimization of multiple conflicting objectives and aligning the gradient updates in a common descent direction. While multi-objective optimization helps avoid conflicting gradient updates, a critical issue is that when there are many objectives, such as in MSP, it is often {\em difficult to find} a common descent direction. This leads to an important question: Is it more effective to separate highly conflicting objectives into different optimization levels or to keep them in a single level? To address this question, this paper investigates three multi-objective MSP formulations, which we refer to as \textbf{objective soup recipes}. These formulations apply multi-objective optimization at different optimization levels to mitigate potential conflicts among all objectives. To keep computation and memory overhead low, we incorporate a lightweight layer‑selection strategy that detects the most conflicting layers and uses only their gradients when computing the conflict‑avoidance direction. We conduct an extensive investigation using the CoVoST v2 dataset for combined multilingual ASR and ST tasks, along with the LibriSpeech and AISHELL-1 datasets for multilingual ASR, to identify highly conflicting objectives and determine the most effective training recipe among the three proposed multi-objective optimization algorithms.

In this paper, we present a novel bilevel optimization-based training approach to training acoustic models for automatic speech recognition (ASR) tasks that we term {bi-level joint unsupervised and supervised training (BL-JUST)}. {BL-JUST employs a lower and upper level optimization with an unsupervised loss and a supervised loss respectively, leveraging recent advances in penalty-based bilevel optimization to solve this challenging ASR problem with affordable complexity and rigorous convergence guarantees.} To evaluate BL-JUST, extensive experiments on the LibriSpeech and TED-LIUM v2 datasets have been conducted. BL-JUST achieves superior performance over the commonly used pre-training followed by fine-tuning strategy.

Recent advances in audio-visual learning have shown promising results in learning representations across modalities. However, most approaches rely on global audio representations that fail to capture fine-grained temporal correspondences with visual frames. Additionally, existing methods often struggle with conflicting optimization objectives when trying to jointly learn reconstruction and cross-modal alignment. In this work, we propose CAV-MAE Sync as a simple yet effective extension of the original CAV-MAE [14] framework for self-supervised audiovisual learning. We address three key challenges: First, we tackle the granularity mismatch between modalities by treating audio as a temporal sequence aligned with video frames, rather than using global representations. Second, we resolve conflicting optimization goals by separating contrastive and reconstruction objectives through dedicated global tokens. Third, we improve spatial localization by introducing learnable register tokens that reduce the semantic load on patch tokens. We evaluate the proposed approach on AudioSet, VGG Sound, and the ADE20K Sound dataset on zero-shot retrieval, classification, and localization tasks demonstrating state-of-the-art performance and outperforming more complex architectures. Code is available at https://github.com/edsonroteia/cav-mae-sync.

The emergence of industrial-scale automatic speech recognition (ASR) models such as Whisper and USM, trained on 1M hours of weakly labelled and 12M hours of audio only proprietary data respectively, has led to a stronger need for large scale public ASR corpora and competitive open source pipelines. Unlike the said models, large language models are typically based on Transformer decoders, and it remains unclear if decoder-only models trained on public data alone can deliver competitive performance. In this work, we investigate factors such as choice of training datasets and modeling components necessary for obtaining the best performance using only public English ASR corpora. Our Decoder-Only Transformer for ASR (DOTA) model comprehensively outperforms the encoder-decoder open source replication of Whisper (OWSM) on nearly all English ASR benchmarks and outperforms Whisper large-v3 on 6 out of 15 test sets. We release our codebase and model checkpoints under permissive license.

Non-autoregressive (NAR) modeling has gained significant interest in speech processing since these models achieve dramatically lower inference time than autoregressive (AR) models while also achieving good transcription accuracy. Since NAR automatic speech recognition (ASR) models must wait for the completion of the entire utterance before processing, some works explore streaming NAR models based on blockwise attention for low-latency applications. However, streaming NAR models significantly lag in accuracy compared to streaming AR and non-streaming NAR models. To address this, we propose a streaming "semi-autoregressive" ASR model that incorporates the labels emitted in previous blocks as additional context using a Language Model (LM) subnetwork. We also introduce a novel greedy decoding algorithm that addresses insertion and deletion errors near block boundaries while not significantly increasing the inference time. Experiments show that our method outperforms the existing streaming NAR model by 19% relative on Tedlium2, 16%/8% on Librispeech-100 clean/other test sets, and 19%/8% on the Switchboard(SWB)/Callhome(CH) test sets. It also reduced the accuracy gap with streaming AR and non-streaming NAR models while achieving 2.5x lower latency. We also demonstrate that our approach can effectively utilize external text data to pre-train the LM subnetwork to further improve streaming ASR accuracy.

To enable the capability of speech models across multiple languages, training multilingual, multi-task automatic speech recognition (ASR) models has gained growing interest. However, different languages and tasks result in distinct training objectives, potentially leading to conflicts during training and degrading the model's performance. To overcome this issue, we introduce M2ASR, a multilingual, multi-task ASR framework, which formulates the problem as a constrained multi-objective optimization (MOO), where multilingual multi-task supervised training augmented by speech-to-text translation (S2TT) serve as supervised objectives and are subject to the desired performance of multilingual unsupervised training. We employ MOO techniques to avoid conflicts among multiple linguistic representations and tasks during training. Extensive experiments demonstrate that M2ASR outperforms conventional multilingual ASR models by 28.3% to 38.6% across diverse ASR tasks.

In this paper we investigate several techniques for improving the performance of RNN transducer (RNNT) acoustic models for conversational speech recognition and report state-of-the-art word error rates (WERs) on the 2000-hour Switchboard dataset. We show that n-best label smoothing and length perturbation which show improved performance on the smaller 300-hour dataset are also very effective on large datasets. We further give a rigorous theoretical interpretation of the n-best label smoothing based on stochastic approximation for training RNNT under the maximum likelihood criterion. Random quantization is also introduced to improve the generalization of RNNT models. On the 2000-hour Switchboard dataset, we report a single model performance of 4.9% and 7.7% WERs on the Switchboard and CallHome portions of NIST Hub5 2000, 7.1% on NIST Hub5 2001 and 6.8% on NIST RT03, without using external LMs.

Soft random sampling (SRS) is a simple yet effective approach for efficient training of large-scale deep neural networks when dealing with massive data. SRS selects a subset uniformly at random with replacement from the full data set in each epoch. In this paper, we conduct a theoretical and empirical analysis of SRS. First, we analyze its sampling dynamics including data coverage and occupancy. Next, we investigate its convergence with non-convex objective functions and give the convergence rate. Finally, we provide its generalization performance. We empirically evaluate SRS for image recognition on CIFAR10 and automatic speech recognition on Librispeech and an in-house payload dataset to demonstrate its effectiveness. Compared to existing coreset-based data selection methods, SRS offers a better accuracy-efficiency trade-off. Especially on real-world industrial scale data sets, it is shown to be a powerful training strategy with significant speedup and competitive performance with almost no additional computing cost.