Filter-based Discriminative Autoencoders for Children Speech Recognition
원문 초록
Children speech recognition is indispensable but challenging due to the diversity of children's speech. In this paper, we propose a filter-based discriminative autoencoder for acoustic modeling. To filter out the influence of various speaker types and pitches, auxiliary information of the speaker and pitch features is input into the encoder together with the acoustic features to generate phonetic embeddings. In the training phase, the decoder uses the auxiliary information and the phonetic embedding extracted by the encoder to reconstruct the input acoustic features. The autoencoder is trained by simultaneously minimizing the ASR loss and feature reconstruction error. The framework can make the phonetic embedding purer, resulting in more accurate senone (triphone-state) scores. Evaluated on the test set of the CMU Kids corpus, our system achieves a 7.8% relative WER reduction compared to the baseline system. In the domain adaptation experiment, our system also outperforms the baseline system on the British-accent PF-STAR task.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
OpusLM: A Family of Open Unified Speech Language Models
State-Space Models in Efficient Whispered and Multi-dialect Speech Recognition
Automatic Speech Recognition Biases in Newcastle English: an Error Analysis
BUT System for the MLC-SLM Challenge
Qwen vs. Gemma Integration with Whisper: A Comparative Study in Multilingual SpeechLLM Systems
Mlphon: A Multifunctional Grapheme-Phoneme Conversion Tool Using Finite State Transducers
토론
이 논문과 연결된 포럼 글이 아직 없습니다.