Context-Aware Interleaved Batching for WhisperX proposes a new batching strategy that combines WhisperX’s fast intra-audio batching with Whisper’s sequential context retention. By using voice activity detection (VAD) to define segment boundaries, the algorithm stabilizes Whisper’s text conditioning and preserves continuous historical context across batched audio segments. Experiments on long‑form audio benchmarks show reduced Word Error Rate and improved proper noun transcription while maintaining high‑throughput inference speeds.
arXiv:2604. 19635v2 Announce Type: replace-cross Abstract: While generative models have set new benchmarks for Target Speaker Extraction (TSE), their inherent reliance on global context precludes deployment in real-time applications.
arXiv:2608. 08569v1 Announce Type: new Abstract: Recent advancements in Speech Large Language Models have demonstrated remarkable capabilities in understanding complex audio tasks.
arXiv:2603.26246v2 Announce Type: replace-cross Abstract: Standard LLM-based speech recognition systems process utterances in isolation, limiting their ability to leverage conversational context. Her...
The paper introduces TextPro‑SLM, a speech large language model that reduces the modality gap by making spoken input resemble a prosody‑aware text LLM. It combines WhisperPro, a unified speech encoder that outputs synchronized text tokens and prosody embeddings, with an LLM backbone that retains the semantic power of the original text LLM while learning paralinguistic cues. Experiments demonstrate that TextPro‑SLM achieves the lowest modality gap among leading SLMs at both 3B and 7B scales, and performs strongly on paralinguistic understanding tasks using only about 1,000 hours of audio for training.
arXiv:2604.06487v2 Announce Type: replace Abstract: Conventional end-to-end automatic speech recognition (ASR) systems rely on paired speech-text data for domain adaptation. Recent LLM-based ASR arch...
arXiv:2608.22196v1 Announce Type: cross Abstract: While cascaded multi-talker ASR (MT-ASR) leverages state-of-the-art foundation models, its performance is often capped by speaker leakage during sepa...
The paper introduces Murmur, an inference system that uses hierarchical chunking to improve long-form automatic speech recognition (ASR). By decoding intermediate target chunks in parallel and employing a fast short-window ASR for speculative drafting, Murmur achieves a 2.5× reduction in end-to-end latency while also lowering tcpWER by 1.9 points on average across English and Mandarin meeting datasets.
arXiv:2607. 20086v1 Announce Type: cross Abstract: State-space sequence models are attractive for streaming speech because they maintain compact recurrent state, but scan-style training kernels can have unfavorable constants for short audio tasks.
arXiv:2606. 13121v1 Announce Type: cross Abstract: Simultaneous speech-to-speech translation aims to enable near-real-time communication by minimizing latency, offering a compelling, real-time alternative to the high latency of consecutive translation.
arXiv:2511. 20973v2 Announce Type: replace-cross Abstract: Large Audio Language Models (LALMs) deliver strong performance across speech and audio tasks, but their audio encoders generate high-rate token sequences (e.
arXiv:2608. 06424v1 Announce Type: cross Abstract: Speech recordings often contain missing, corrupted, or incorrect regions that must be reconstructed or modified without re-synthesizing the entire utterance.
arXiv:2608.30927v1 Announce Type: cross Abstract: Whisper exposes speech through a fixed 1500-token encoder interface, now a default representation for ASR decoders and Whisper-based speech language...