Weakly Supervised Construction of ASR Systems with Massive Video Data
원문 초록
Building Automatic Speech Recognition (ASR) systems from scratch is significantly challenging, mostly due to the time-consuming and financially-expensive process of annotating a large amount of audio data with transcripts. Although several unsupervised pre-training models have been proposed, applying such models directly might still be sub-optimal if more labeled, training data could be obtained without a large cost. In this paper, we present a weakly supervised framework for constructing ASR systems with massive video data. As videos often contain human-speech audios aligned with subtitles, we consider videos as an important knowledge source, and propose an effective approach to extract high-quality audios aligned with transcripts from videos based on Optical Character Recognition (OCR). The underlying ASR model can be fine-tuned to fit any domain-specific target training datasets after weakly supervised pre-training. Extensive experiments show that our framework can easily produce state-of-the-art results on six public datasets for Mandarin speech recognition.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
NonverbalTTS: A Public English Corpus of Text-Aligned Nonverbal Vocalizations with Emotion Annotations for Text-to-Speech
WhisperKit: On-device Real-time ASR with Billion-Scale Transformers
Lightweight Target-Speaker-Based Overlap Transcription for Practical Streaming ASR
AI-Generated Song Detection via Lyrics Transcripts
End-to-End Spoken Grammatical Error Correction
LM-SPT: LM-Aligned Semantic Distillation for Speech Tokenization
토론
이 논문과 연결된 포럼 글이 아직 없습니다.