4 papers
From Seeing it to Experiencing it: Interactive Evaluation of Intersectional Voice Bias in Human-AI Speech Interaction
Shree Harsha Bokkahalli Satish, Maria Teleki, Christoph Minixhofer +3
SpeechLLMs process spoken language directly from audio, but accent and vocal identity cues can lead to biased behaviour. Current bias evaluations often miss how such bias manifests…
Prosodic Structure Beyond Lexical Content: A Study of Self-Supervised Learning
Sarenne Wallbridge, Christoph Minixhofer, Catherine Lai +1
People exploit the predictability of lexical structures during text comprehension. Though predictable structure is also present in speech, the degree to which prosody, e.g. intonat…
TTSDS2: Resources and Benchmark for Evaluating Human-Quality Text to Speech Systems
Christoph Minixhofer, Ondrej Klejch, Peter Bell
Evaluation of Text to Speech (TTS) systems is challenging and resource-intensive. Subjective metrics such as Mean Opinion Score (MOS) are not easily comparable between works. Objec…
Beyond Oversmoothing: Evaluating DDPM and MSE for Scalable Speech Synthesis in ASR
Christoph Minixhofer, Ondrej Klejch, Peter Bell
Synthetically generated speech has rapidly approached human levels of naturalness. However, the paradox remains that ASR systems, when trained on TTS output that is judged as natur…