Streaming Non-Autoregressive Model for Accent Conversion and Pronunciation Improvement
We propose a first streaming accent conversion (AC) model that transforms non-native speech into a native-like accent while preserving speaker identity, prosody and improving pronunciation. Our approach enables stream processing by modifying a previous AC architecture with an Emformer encoder and an optimized inference mechanism. Additionally, we integrate a native text-to-speech (TTS) model to generate ideal ground-truth data for efficient training. Our streaming AC model achieves comparable performance to the top AC models while maintaining stable latency, making it the first AC system capable of streaming.
Code (0)
등록된 구현이 없습니다.
Tasks
text-to-speechText to SpeechSimilar Papers 제목 키워드 기반
Improving Pronunciation and Accent Conversion through Knowledge Distillation And Synthetic Ground-Truth from Native TTS
Previous approaches on accent conversion (AC) mainly aimed at making non-native speech sound more native while maintaining the original content and speaker identity. However, non-native speakers sometimes have pronunciat…
Knowledge DistillationAn Investigation of Indian Native Language Phonemic Influences on L2 English Pronunciations
Speech systems are sensitive to accent variations. This is especially challenging in the Indian context, with an abundance of languages but a dearth of linguistic studies characterising pronunciation variations. The grow…
High-Fidelity Neural Phonetic Posteriorgrams
A phonetic posteriorgram (PPG) is a time-varying categorical distribution over acoustic units of speech (e.g., phonemes). PPGs are a popular representation in speech generation due to their ability to disentangle pronunc…
Voice ConversionSynthetic Cross-accent Data Augmentation for Automatic Speech Recognition
The awareness for biased ASR datasets or models has increased notably in recent years. Even for English, despite a vast amount of available training data, systems perform worse for non-native speakers. In this work, we i…
Automatic Speech RecognitionData Augmentationspeech-recognitionSpeech RecognitionConvert and Speak: Zero-shot Accent Conversion with Minimum Supervision
Low resource of parallel data is the key challenge of accent conversion(AC) problem in which both the pronunciation units and prosody pattern need to be converted. We propose a two-stage generative framework "convert-and…