Learning Speech Representations with Variational Predictive Coding

Despite being the best known objective for learning speech representations, the HuBERT objective has not been further developed and improved. We argue that it is the lack of an underlying principle that stalls the development, and, in this paper, we show that predictive coding under a variational view is the principle behind the HuBERT objective. Due to its generality, our formulation provides opportunities to improve parameterization and optimization, and we show two simple modifications that bring immediate improvements to the HuBERT objective. In addition, the predictive coding formulation has tight connections to various other objectives, such as APC, CPC, wav2vec, and BEST-RQ. Empirically, the improvement in pre-training brings significant improvements to four downstream tasks: phone classification, f0 tracking, speaker recognition, and automatic speech recognition, highlighting the importance of the predictive coding interpretation.

Three factor delay learning rules for spiking neural networks

Spiking Neural Networks (SNNs) are dynamical systems that operate on spatiotemporal data, yet their learnable parameters are often limited to synaptic weights, contributing little to temporal pattern recognition. Learnable parameters that delay spike times can improve classification performance in temporal tasks, but existing methods rely on large networks and offline learning, making them unsuitable for real-time operation in resource-constrained environments. In this paper, we introduce synaptic and axonal delays to leaky integrate and fire (LIF)-based feedforward and recurrent SNNs, and propose three-factor learning rules to simultaneously learn delay parameters online. We employ a smooth Gaussian surrogate to approximate spike derivatives exclusively for the eligibility trace calculation, and together with a top-down error signal determine parameter updates. Our experiments show that incorporating delays improves accuracy by up to 20% over a weights-only baseline, and for networks with similar parameter counts, jointly learning weights and delays yields up to 14% higher accuracy. On the SHD speech recognition dataset, our method achieves similar accuracy to offline backpropagation-based approaches. Compared to state-of-the-art methods, it reduces model size by 6.6x and inference latency by 67%, with only a 2.4% drop in classification accuracy. Our findings benefit the design of power and area-constrained neuromorphic processors by enabling on-device learning and lowering memory requirements.

Distilled HuBERT for Mobile Speech Emotion Recognition: A Cross-Corpus Validation Study

Speech Emotion Recognition (SER) has significant potential for mobile applications, yet deployment remains constrained by the computational demands of state-of-the-art transformer architectures. This paper presents a mobile-efficient SER system based on DistilHuBERT, a distilled and 8-bit quantized transformer that achieves approximately 92% parameter reduction compared to full-scale Wav2Vec 2.0 models while maintaining competitive accuracy. We conduct a rigorous 5-fold Leave-One-Session-Out (LOSO) cross-validation on the IEMOCAP dataset to ensure speaker independence, augmented with cross-corpus training on CREMA-D to enhance generalization. Cross-corpus training with CREMA-D yields a 1.2% improvement in Weighted Accuracy, a 1.4% gain in Macro F1-score, and a 32% reduction in cross-fold variance, with the Neutral class showing the most substantial benefit at 5.4% F1-score improvement. Our approach achieves an Unweighted Accuracy of 61.4% with a quantized model footprint of only 23 MB, representing approximately 91% of the Unweighted Accuracy of a full-scale baseline. Cross-corpus evaluation on RAVDESS reveals that the theatrical nature of acted emotions causes predictions to cluster by arousal level rather than by specific emotion categories - happiness predictions systematically bleed into anger predictions, and sadness predictions bleed into neutral predictions, due to acoustic saturation when actors prioritize clarity over subtlety. Despite this theatricality effect reducing overall RAVDESS accuracy to 46.64%, the model maintains robust arousal detection with 99% recall for anger, 55% recall for neutral, and 27% recall for sadness. These findings demonstrate a Pareto-optimal tradeoff between model size and accuracy, enabling practical affect recognition on resource-constrained mobile devices.

SITA: Learning Speaker-Invariant and Tone-Aware Speech Representations for Low-Resource Tonal Languages

Tonal low-resource languages are widely spoken yet remain underserved by modern speech technology. A key challenge is learning representations that are robust to nuisance variation such as gender while remaining tone-aware for different lexical meanings. To address this, we propose SITA, a lightweight adaptation recipe that enforces Speaker-Invariance and Tone-Awareness for pretrained wav2vec-style encoders. SITA uses staged multi-objective training: (i) a cross-gender contrastive objective encourages lexical consistency across speakers, while a tone-repulsive loss prevents tone collapse by explicitly separating same-word different-tone realizations; and (ii) an auxiliary Connectionist Temporal Classification (CTC)-based ASR objective with distillation stabilizes recognition-relevant structure. We evaluate primarily on Hmong, a highly tonal and severely under-resourced language where off-the-shelf multilingual encoders fail to represent tone effectively. On a curated Hmong word corpus, SITA improves cross-gender lexical retrieval accuracy, while maintaining usable ASR accuracy relative to an ASR-adapted XLS-R teacher. We further observe similar gains when transferring the same recipe to Mandarin, suggesting SITA is a general, plug-in approach for adapting multilingual speech encoders to tonal languages.

Index-ASR Technical Report

Automatic speech recognition (ASR) has witnessed remarkable progress in recent years, largely driven by the emergence of LLM-based ASR paradigm. Despite their strong performance on a variety of open-source benchmarks, existing LLM-based ASR systems still suffer from two critical limitations. First, they are prone to hallucination errors, often generating excessively long and repetitive outputs that are not well grounded in the acoustic input. Second, they provide limited support for flexible and fine-grained contextual customization. To address these challenges, we propose Index-ASR, a large-scale LLM-based ASR system designed to simultaneously enhance robustness and support customizable hotword recognition. The core idea of Index-ASR lies in the integration of LLM and large-scale training data enriched with background noise and contextual information. Experimental results show that our Index-ASR achieves strong performance on both open-source benchmarks and in-house test sets, highlighting its robustness and practicality for real-world ASR applications.

Enhancing Fully Formatted End-to-End Speech Recognition with Knowledge Distillation via Multi-Codebook Vector Quantization

Conventional automatic speech recognition (ASR) models typically produce outputs as normalized texts lacking punctuation and capitalization, necessitating post-processing models to enhance readability. This approach, however, introduces additional complexity and latency due to the cascaded system design. In response to this challenge, there is a growing trend to develop end-to-end (E2E) ASR models capable of directly predicting punctuation and capitalization, though this area remains underexplored. In this paper, we propose an enhanced fully formatted E2E ASR model that leverages knowledge distillation (KD) through multi-codebook vector quantization (MVQ). Experimental results demonstrate that our model significantly outperforms previous works in word error rate (WER) both with and without punctuation and capitalization, and in punctuation error rate (PER). Evaluations on the LibriSpeech-PC test-clean and test-other subsets show that our model achieves state-of-the-art results.

PROFASR-BENCH: A Benchmark for Context-Conditioned ASR in High-Stakes Professional Speech

Automatic Speech Recognition (ASR) in professional settings faces challenges that existing benchmarks underplay: dense domain terminology, formal register variation, and near-zero tolerance for critical entity errors. We present ProfASR-Bench, a professional-talk evaluation suite for high-stakes applications across finance, medicine, legal, and technology. Each example pairs a natural-language prompt (domain cue and/or speaker profile) with an entity-rich target utterance, enabling controlled measurement of context-conditioned recognition. The corpus supports conventional ASR metrics alongside entity-aware scores and slice-wise reporting by accent and gender. Using representative families Whisper (encoder-decoder ASR) and Qwen-Omni (audio language models) under matched no-context, profile, domain+profile, oracle, and adversarial conditions, we find a consistent pattern: lightweight textual context produces little to no change in average word error rate (WER), even with oracle prompts, and adversarial prompts do not reliably degrade performance. We term this the context-utilization gap (CUG): current systems are nominally promptable yet underuse readily available side information. ProfASR-Bench provides a standardized context ladder, entity- and slice-aware reporting with confidence intervals, and a reproducible testbed for comparing fusion strategies across model families. Dataset: https://huggingface.co/datasets/prdeepakbabu/ProfASR-Bench Code: https://github.com/prdeepakbabu/ProfASR-Bench

VALLR-Pin: Dual-Decoding Visual Speech Recognition for Mandarin with Pinyin-Guided LLM Refinement

Visual Speech Recognition aims to transcribe spoken words from silent lip-motion videos. This task is particularly challenging for Mandarin, as visemes are highly ambiguous and homophones are prevalent. We propose VALLR-Pin, a novel two-stage framework that extends the recent VALLR architecture from English to Mandarin. First, a shared video encoder feeds into dual decoders, which jointly predict both Chinese character sequences and their standard Pinyin romanization. The multi-task learning of character and phonetic outputs fosters robust visual-semantic representations. During inference, the text decoder generates multiple candidate transcripts. We construct a prompt by concatenating the Pinyin output with these candidate Chinese sequences and feed it to a large language model to resolve ambiguities and refine the transcription. This provides the LLM with explicit phonetic context to correct homophone-induced errors. Finally, we fine-tune the LLM on synthetic noisy examples: we generate imperfect Pinyin-text pairs from intermediate VALLR-Pin checkpoints using the training data, creating instruction-response pairs for error correction. This endows the LLM with awareness of our model's specific error patterns. In summary, VALLR-Pin synergizes visual features with phonetic and linguistic context to improve Mandarin lip-reading performance.

TICL+: A Case Study On Speech In-Context Learning for Children's Speech Recognition

Children's speech recognition remains challenging due to substantial acoustic and linguistic variability, limited labeled data, and significant differences from adult speech. Speech foundation models can address these challenges through Speech In-Context Learning (SICL), allowing adaptation to new domains without fine-tuning. However, the effectiveness of SICL depends on how in-context examples are selected. We extend an existing retrieval-based method, Text-Embedding KNN for SICL (TICL), introducing an acoustic reranking step to create TICL+. This extension prioritizes examples that are both semantically and acoustically aligned with the test input. Experiments on four children's speech corpora show that TICL+ achieves up to a 53.3% relative word error rate reduction over zero-shot performance and 37.6% over baseline TICL, highlighting the value of combining semantic and acoustic information for robust, scalable ASR in children's speech.

Phoneme-based speech recognition driven by large language models and sampling marginalization

Recently, the Large Language Model-based Phoneme-to-Grapheme (LLM-P2G) method has shown excellent performance in speech recognition tasks and has become a feasible direction to replace the traditional WFST decoding method. This framework takes into account both recognition accuracy and system scalability through two-stage modeling of phoneme prediction and text generation. However, the existing LLM-P2G adopts the Top-K Marginalized (TKM) training strategy, and its candidate phoneme sequences rely on beam search generation, which has problems such as insufficient path diversity, low training efficiency, and high resource overhead. To this end, this paper proposes a sampling marginalized training strategy (Sampling-K Marginalized, SKM), which replaces beam search with random sampling to generate candidate paths, improving marginalized modeling and training efficiency. Experiments were conducted on Polish and German datasets, and the results showed that SKM further improved the model learning convergence speed and recognition performance while maintaining the complexity of the model. Comparative experiments with a speech recognition method that uses a projector combined with a large language model (SpeechLLM) also show that the SKM-driven LLM-P2G has more advantages in recognition accuracy and structural simplicity. The study verified the practical value and application potential of this method in cross-language speech recognition systems.