Speech Recognition

Tool-augmented speech assistants typically serialize automatic speech recognition, large language model inference, and external tool execution. As a result, tool latency is incurred only after the user has finished speak…

Speech Recognition

Q-SPT: Learnable Query-Based Compression for Low-Frame-Rate Speech Tokenization

2026-10-01 · Jeeyoung Yun, Seohwan Yun, Sungwoong Kim arxiv

Neural speech codecs increasingly serve as tokenizers for speech language models (SLMs). Lowering the frame rate reduces the computational and memory costs of SLMs, but makes it difficult to preserve both linguistic info…

Speech Recognition

SHAMS: An Audio-Grounded Pronunciation Benchmark for Levantine Arabic

2026-10-01 · Ben Sapirstein, Roy Mattar, Guy Mor-Lan, Ahlam Mohamed 외 arxiv

Levantine Arabic (LA) is spoken by tens of millions of people, creating a pressing need for shared benchmarks to evaluate LA speech-language technologies. Evaluating such technology is particularly challenging given LA's…

Speech Recognition

Pruned CTC for Memory-Efficient Large-Vocabulary ASR Training

2026-09-27 · Yifan Yang, Xiaoyu Yang, Zengrui Jin, Xian Shi 외 hf

Connectionist temporal classification (CTC) naturally supports offline and streaming speech recognition with utterance-level supervision, but conventional implementations materialize frame-by-vocabulary activations in me…

Speech Recognition

NVAlign: Direct-Gradient Optimization for Non-Verbal Control in Continuous Autoregressive Flow Matching Text-to-Speech

2026-09-25 · Qiaolin Wang, Pedro Sandoval-Segura, Anunaya Joshi, Edvardas Jurkonis 외 hf

While modern text-to-speech (TTS) systems generate highly natural speech and support inline non-verbal vocalization (NVV) tags, accurate control over these events remains challenging. A key gap is the lack of established…

Speech Recognition

OmniVChat: Synthesizing, Benchmarking, and Training for Native Audio-Visual Dialogue

2026-09-18 · Haolin He, Yunfei Chu, Qi Chen, Wen Huang 외 hf

We define OmniVChat (Omni Video Chat) as the task of native audio-visual dialogue between a user and an omni model. In OmniVChat, omni models directly and simultaneously receive audio and video from a user and return tex…

Reinforcement Learning Speech Recognition Video Generation

전체 7,133편 보기 →