Sometin Beta Pass Notin (SBPN): 通过知识蒸馏改进尼日利亚语言的多语言语音识别
Sometin Beta Pass Notin: Improving Multilingual ASR for Nigerian Languages via Knowledge Distillation
AI总结：
本文提出SBPN模型，通过两阶段知识蒸馏方法提升尼日利亚多种语言的语音识别性能，显著降低词错误率并优于现有多语言模型。
摘要：
尽管现代多语言自动语音识别（ASR）系统支持多种尼日利亚语言，但其性能始终落后于英语和法语等高资源语言。尼日利亚语言存在独特的建模挑战，包括数据稀缺、不一致的正字法、声调符号、多样化的口音、频繁的代码切换和本地化专有名词。为解决这些挑战，我们开发了一个多语言ASR框架，采用两阶段蒸馏过程。首先，我们利用学生-教师知识蒸馏从现有单语言模型中学习，基于稳健的语言特定N-gram语言模型进行条件化。其次，我们使用伪标签数据进行迭代自我改进以进一步提高准确性。我们的方法显著缩小了性能差距，平均在单语言基线上实现了29%的词错误率（WER）减少。我们的模型在主要基准上也优于现有最先进的多语言模型，包括Common Voice和Fleurs。我们引入Sometin Beta Pass Notin（SBPN），一个覆盖约鲁巴、豪萨、伊博、尼日利亚皮钦语和尼日利亚英语的多语言ASR模型。SBPN以两种大小发布：SBPN-Base（120 M参数）和SBPN-Large（600 M参数）。通过发布这些作为开放基础模型，我们旨在为该地区丰富的语音和文化景观的研究提供ASR资源。
英文摘要：
Although modern multilingual Automatic Speech Recognition (ASR) systems support several Nigerian languages, their performance consistently lags behind resource-rich languages such as English and French. Nigerian languages present unique modelling hurdles, including acute data scarcity, inconsistent orthography, tonal diacritics, diverse accents, frequent code-switching, and localised named entities. To address these challenges, we developed a multilingual ASR framework using a two-stage distillation process. First, we employed student-teacher knowledge distillation from existing monolingual models, conditioned on robust language-specific N-gram language models. Second, we performed iterative self improvement using pseudo-labelled data to further refine accuracy. Our method significantly bridges the performance gap, achieving on average a reduction in the relative Word Error Rate (WER) of 29% over the monolingual baselines. Our models also outperform state-of-the-art multilingual models across major benchmarks, including Common Voice and FLEURS. We introduce Sometin Beta Pass Notin (SBPN), a multilingual foundational ASR model that covers Yorùbá, Hausa, Igbo, Nigerian Pidgin, and Nigerian English.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
