Emotional prosody in LM-TTS localizes to the x-vector by elimination, where centroid arithmetic on speaker embeddings yields training-free cross-lingual gains of +0.29 emotion2vec cosine on English and +0.09 on Brazilian Portuguese while preserving identity.
hub
11 Task Vectors for Emotion Control in LM-TTS Brecht Desplanques, Jenthe Thienpondt, and Kris Demuynck
5 Pith papers cite this work, alongside 2,662 external citations. Polarity classification is still indexing.
5
Pith papers citing it
2,662
external citations · external index
hub tools
representative citing papers
CleanCodec reframes audio tokenization as a selective information bottleneck to encode only perceptually important features at 12.5 tokens per second, outperforming prior codecs in efficiency, speaker similarity, and intelligibility.
SpeakerLLM unifies speaker profiling, recording-condition understanding, and structured verification reasoning in an audio-LLM via a hierarchical tokenizer and decision traces.
Listeners detect automatic anonymization in pathological speech at 91-93% accuracy with a 30-point perceived quality drop, yet clinical severity ratings stay nearly unchanged for dysarthria, dysglossia, and dysphonia.
Post-processing with an encoder-decoder model yields 22% relative EER reduction on normal-vs-whispered trials and 1.88% EER on whispered-vs-whispered, outperforming ReDimNet-B2.
citing papers explorer
-
Task-Vector Arithmetic for Emotional Expressivity Control in Language-Model-Based Text-to-Speech
Emotional prosody in LM-TTS localizes to the x-vector by elimination, where centroid arithmetic on speaker embeddings yields training-free cross-lingual gains of +0.29 emotion2vec cosine on English and +0.09 on Brazilian Portuguese while preserving identity.
-
CleanCodec: Efficient and Robust Speech Tokenization via Perceptually Guided Encoding
CleanCodec reframes audio tokenization as a selective information bottleneck to encode only perceptually important features at 12.5 tokens per second, outperforming prior codecs in efficiency, speaker similarity, and intelligibility.
-
SpeakerLLM: A Speaker-Specialized Audio-LLM for Speaker Understanding and Verification Reasoning
SpeakerLLM unifies speaker profiling, recording-condition understanding, and structured verification reasoning in an audio-LLM via a hierarchical tokenizer and decision traces.
-
Perceptual implications of automatic anonymization in pathological speech
Listeners detect automatic anonymization in pathological speech at 91-93% accuracy with a 30-point perceived quality drop, yet clinical severity ratings stay nearly unchanged for dysarthria, dysglossia, and dysphonia.
-
Enhancing Speaker Verification with Whispered Speech via Post-Processing
Post-processing with an encoder-decoder model yields 22% relative EER reduction on normal-vs-whispered trials and 1.88% EER on whispered-vs-whispered, outperforming ReDimNet-B2.