mlsanityData to 7 Oct 2026

Pitch-Aware RNN-T for Mandarin Chinese Mispronunciation Detection and Diagnosis

arXiv 2406.04595 ↗First posted 7 Jun 2024cs.SD cs.CL eess.AScited by 0

Not on the map. Why?

Abstract (arXiv)

Mispronunciation Detection and Diagnosis (MDD) systems, leveraging Automatic Speech Recognition (ASR), face two main challenges in Mandarin Chinese: 1) The two-stage models create an information gap between the phoneme or tone classification stage and the MDD stage. 2) The scarcity of Mandarin MDD datasets limits model training. In this paper, we introduce a stateless RNN-T model for Mandarin MDD, utilizing HuBERT features with pitch embedding through a Pitch Fusion Block. Our model, trained solely on native speaker data, shows a 3% improvement in Phone Error Rate and a 7% increase in False Acceptance Rate over the state-of-the-art baseline in non-native scenarios

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 11 of its 34 references that are in the map. First posted on arXiv 7 Jun 2024.

Builds on

11 of 34 references.

References · 11

  1. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  2. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,301
  3. 2018Group Normalizationcited by 1,514
  4. 2017AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baselinecited by 364
  5. 2023Zipformer: A faster and better encoder for automatic speech recognitioncited by 77
  6. 2021speechocean762: An Open-Source Non-native English Speech Corpus For Pronunciation Assessmentcited by 57
  7. 2021Lhotse: a speech data representation library for the modern deep learning ecosystemcited by 33
  8. 2020An End-to-End Mispronunciation Detection System for L2 English Speech Leveraging Novel Anti-Phone Modelingcited by 18
  9. 2023Zero-Shot Automatic Pronunciation Assessmentcited by 5
  10. 2022Xiaoicesing 2: A High-Fidelity Singing Voice Synthesizer Based on Generative Adversarial Networkcited by 3
  11. 2023CrossSinger: A Cross-Lingual Multi-Singer High-Fidelity Singing Voice Synthesizer Trained on Monolingual Singerscited by 2

Built on by

Not cited yet.