论文解读
AVI-Bench: Toward Human-like Audio-Visual Intelligence of Omni-MLLMs
语音识别 | 8.8/10
语音识别
论文解读
Bridging Traditional Explainability Methods and Multimodal Multilingual Models: An XAI-Based Analysis
语音识别 | 5.4/10
论文解读
Cross-Modal Masking for Robust Silent Speech Synthesis Using sEMG and Lipreading
语音合成 | 7.5/10
论文解读
Factors affecting ASR performance: A study using state of the art ASR models in Indic Languages
语音识别 | 6.9/10
论文解读
Is Text All You Need? Text as a Universal Information Bottleneck for Speech LLMs
语音识别 | 7.6/10
论文解读
Overcoming Decoder Inconsistencies in Whisper for Dravidian and Low-Resource Languages
语音识别 | 6.2/10
论文解读
Parameter-Efficient Continual Learning for Automatic Speech Recognition
语音识别 | 8.1/10
论文解读
Subtitle-Aligned Fine-Tuning of Whisper for Swiss German ASR: Benchmark Contamination, Convention Mismatch, and an Honest Baseline at 25.6% WER (13.8% cWER)
语音识别 | 8.2/10
论文解读
Assessing True Generalisability of Audio-Visual Speech Recognisers
语音识别 | 9.5/10
论文解读
Contrastive Training with LLM-generated Near-Misses for Robust Code-Switching Speech Recognition
语音识别 | 7.1/10
论文解读
Hearing the Unspoken: Language Model Priors for Acoustic Adversarial Attacks
语音识别 | 9.2/10
论文解读
Phonetic Error Analysis of Raw Waveform Acoustic Models
语音识别 | 7.6/10
论文解读
Whisper Hallucination Detection and Mitigation via Hidden Representation Steering and Sparse AutoEncoders
语音识别 | 7.9/10
论文解读
Age-Aware Adapter Tuning for Children's Speech Recognition
语音识别 | 8.4/10
论文解读
Automatic Labelling of Speech Translation Errors
语音识别 | 6.1/10
论文解读
Beyond Waveform Robustness: Robust Feature-Vocoder Adversarial Attacks on Automatic Speech Recognition
语音识别 | 7.5/10
论文解读
Beyond WER: A Paired Acoustic Stress Test for Ambient Clinical Scribes
语音识别 | 7.1/10
论文解读
CoSTA: Cognitive-State-Conditioned TTS Data Augmentation Using ASR Transcripts for Alzheimer's Disease Detection
语音合成 | 6.5/10
论文解读
F3-Tokenizer: Taming Audio Autoencoder Latents for Understanding and Generation
语音合成 | 7.2/10
论文解读
FiLM-Based Speaker Conditioning of a SpeechLLM for Pathological Speech Recognition
语音识别 | 8.0/10