论文解读
Enhancing Law-Enforcement Audio Transcription: A LoRA-Based Adaptation of Whisper for BWC Footage
语音识别 | 4.8/10
语音识别
论文解读
Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens
语音识别 | 6.3/10
论文解读
Voice Memory for Agentic Speech Recognition
语音识别 | 8.2/10
论文解读
Evaluation of forced alignment of code-mixed speech: the case of Hindi-English
语音识别 | 5.4/10
论文解读
SpeechLLM Meets Federated Learning for End-to-End ASR: English and Italian Case Studies
语音识别 | 7.1/10
论文解读
Towards Operational Conversational Intelligence: A Speech Intelligence Framework
说话人日志 | 6.4/10
论文解读
Earnings25: A Comprehensive 500-Hour Speech Benchmark for Finance
语音识别 | 7.1/10
论文解读
Indic DiarBench: A Multilingual Joint Diarization and ASR Benchmark for Indian Languages
说话人日志 | 7.1/10
论文解读
MoLGE: Mixture of Language Group Experts for Efficient Scaling of Massively Multilingual Speech Recognition
语音识别 | 6.7/10
论文解读
Listen, Do Not Copy: Internalizing Audio-Grounded Scaffold Context for Robust Omni-Model Speech Understanding
语音识别 | 6.6/10
论文解读
MEUSLI: a Multilingual Projector for LLM-based ASR and Beyond
语音识别 | 8.2/10
论文解读
DONDO: Open w2v-BERT Speech-Recognition Base Models for African Languages
语音识别 | 8.1/10
论文解读
From Read Speech to Spoken Digits: A Task-Specific Evaluation of Speech Privacy With Informed Attackers
语音识别 | 7.5/10
论文解读
Phonetic forced alignment for low-resource language varieties: Model training and evaluation on Chengdu Mandarin
语音识别 | 6.2/10
论文解读
VibeVoice-ASR-BitNet Technical Report
语音识别 | 7.8/10
论文解读
Benchmarking Human and Automatic Speech Recognition of Diverse Speech: Initial Results
语音识别 | 7.0/10
论文解读
Constrained CTC Decoding for Efficient Diacritic Restoration
语音识别 | 7.7/10
论文解读
From a Multilingual Streaming ASR Backbone to Kenyan-Language Systems: Data-Centric Adaptation of Nemotron 3.5 for Kikuyu, Dholuo, and Kalenjin
语音识别 | 6.5/10
论文解读
Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing
语音识别 | 7.1/10
论文解读
What the Waveform Knows: Transparent-first Speech and Audio Intelligence with Caption Studio
语音识别 | 4.8/10