← Back to all news
arXiv Computation and Language By Carlos Bain, Max Bain

Context-Aware Interleaved Batching for WhisperX

Read the original on arXiv Computation and Language →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Related stories

arXiv AI
Jul 7

StarTSE: Towards Streaming Target Speaker Extraction via Chunk-wise Interleaved Splicing of Autoregressive Language Model

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.

By Shuhai Peng, Hui Lu, Jinjiang Liu, Liyang Chen, Guiping Zhong, Jiakui Li, Huimeng Wang, Haiyun Li, Liang Cao, Shiyin Kang, Zhiyong Wu
llmsbenchmarks
More like this →
arXiv AI
Oct 21

Abstract Compression of Conversational Audio Context for LLM-based ASR

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...

By Shashi Kumar, Esa\'u Villatoro-Tello, Sergio Burdisso, Kadri Hacioglu, Thibault Ba\~neras-Roux, Hasindri Watawana, Dairazalia Sanchez-Cortes, Srikanth Madikeri, Petr Motlicek, Andreas Stolcke
llmsragmultimodal
More like this →
arXiv Computation and Language
5d ago

Minimizing Modality Gap from the Input Side: Your Speech LLM Can Be a Prosody-Aware Text LLM

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.

By Wenqian Cui, Xiao-Hui Li, Daxin Tan, Qiyong Zheng, Irwin King
llmsrag
More like this →
arXiv Computation and Language
Sep 22

Closing the Speech-Text Gap with Limited Audio for Effective Domain Adaptation in LLM-Based ASR

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...

By Thibault Ba\~neras-Roux, Sergio Burdisso, Esa\'u Villatoro-Tello, Dairazalia S\'anchez-Cort\'es, Shiran Liu, Severin Baroudi, Shashi Kumar, Hasindri Watawana, Manjunath K E, Kadri Hacioglu, Petr Motlicek, Andreas Stolcke
llmsfine-tuningmultimodalsafety
More like this →