arXiv:2609.05871v1 Announce Type: cross Abstract: Audio-conditioned language models often underuse acoustic cues such as prosody, emotion, and non-speech sounds, raising the question of whether ASR-s...
arXiv:2609.18533v1 Announce Type: new Abstract: Automatic speech recognition (ASR) systems exhibit unequal error rates across speaker groups, motivating interventions on their internal representation...
Automatic speech recognition (ASR) systems exhibit unequal error rates across speaker groups, motivating interventions on their internal representations. We ask whether speaker-linked attributes that...
The paper introduces a training‑free, inference‑time technique to curb hallucinated transcripts in Whisper by projecting decoder activations away from a low‑rank hallucination subspace derived from non‑speech data. Two variants are tested: an always‑on projection that dramatically lowers hallucination rates on non‑speech benchmarks, and a gated version that applies the projection only when non‑speech is predicted, achieving a smaller but still significant reduction. On LibriSpeech, the gated method slightly increases word error rate but keeps false‑rejection rates low, demonstrating a controllable trade‑off between hallucination suppression and recognition accuracy.
arXiv:2607. 11801v1 Announce Type: cross Abstract: Large audio-language models (LALMs) often underperform on fine-grained, non-semantic attributes of speech, such as a speaker's emotion, despite strong performance on speech content.
The paper investigates whether audio‑language models capture paralinguistic cues beyond spoken content. Using the Expresso dataset and four open‑source models, the authors trace how speaking style information is encoded in the late layers of the audio encoder but is degraded before reaching the final output. They find that some models are content‑driven while others are acoustic‑driven, revealing a gap between what is encoded and what is utilized in current audio‑language models.
arXiv:2607. 13013v1 Announce Type: new Abstract: Automatic speech recognition is dominated by autoregressive decoders that emit one token at a time.
arXiv:2609.38897v1 Announce Type: cross Abstract: Far-field automatic speech recognition(ASR) degrades under reverberation, noise, and talker motion, yet the benchmarks that drive model selection emp...
arXiv:2606. 06559v1 Announce Type: cross Abstract: Full-duplex spoken dialogue models allow voice agents to listen and speak concurrently, enabling natural interaction with real-time overlap.
arXiv:2609.36500v1 Announce Type: cross Abstract: Speaker verification systems encounter combinations of noise, channel distortion, and changes in speech. Evaluating each condition separately does no...
arXiv:2603. 02794v2 Announce Type: replace-cross Abstract: We present TVF (Time-Varying Filtering), an interpretable, low-latency speech enhancement model for real-time, on-device assistive hearing.
arXiv:2606. 27543v1 Announce Type: cross Abstract: The variations in vocal effort range (e.