跨领域特定数据集对阿肯语ASR模型进行基准评测：性能、可扩展性与适应性的比较评估
Benchmarking Akan ASR Models Across Domain-Specific Datasets: A Comparative Evaluation of Performance, Scalability, and Adaptability
AI总结：
本研究通过四个多领域阿肯语语音语料库对七种基于Whisper和Wav2Vec2的ASR模型进行基准评测，揭示其领域依赖性及错误行为差异，并提出领域适应、自适应路由和多语言训练等改进方向。
摘要：
现有的大多数自动语音识别（ASR）研究使用领域内数据集评估模型，但很少评估模型在不同语音语境中的泛化能力。本研究通过使用四个阿肯语语音语料库，对基于Whisper和Wav2Vec2等transformer架构构建的七个阿肯语ASR模型进行基准评测，以确定其性能，从而填补这一空白。这些数据集涵盖多个领域，包括具有文化相关性的图像描述、非正式对话、圣经经文朗读和自发性金融对话。对词错误率和字符错误率的比较凸显了领域依赖性，模型仅在其训练领域内表现最佳，而在不匹配场景中准确率明显下降。本研究还识别出Whisper和Wav2Vec2架构之间不同的错误行为。微调后的Whisper阿肯语模型会产生更流畅但可能具有误导性的转录错误，而Wav2Vec2在遇到不熟悉的输入时会产生更明显但更难解释的输出。在为低资源语言（LRL）应用选择架构时，应考虑ASR错误在可读性与透明性之间的这种权衡。这些发现表明，需要针对阿肯语和其他低资源语言开发有针对性的领域适应技术、自适应路由策略和多语言训练框架。
英文摘要：
Most existing automatic speech recognition (ASR) research evaluate models using in-domain datasets. However, they seldom evaluate how they generalize across diverse speech contexts. This study addresses this gap by benchmarking seven Akan ASR models built on transformer architectures, such as Whisper and Wav2Vec2, using four Akan speech corpora to determine their performance. These datasets encompass various domains, including culturally relevant image descriptions, informal conversations, biblical scripture readings, and spontaneous financial dialogues. A comparison of the word error rate and character error rate highlighted domain dependency, with models performing optimally only within their training domains while showing marked accuracy degradation in mismatched scenarios. This study also identified distinct error behaviors between the Whisper and Wav2Vec2 architectures. Whereas fine-tuned Whisper Akan models led to more fluent but potentially misleading transcription errors, Wav2Vec2 produced more obvious yet less interpretable outputs when encountering unfamiliar inputs. This trade-off between readability and transparency in ASR errors should be considered when selecting architectures for low-resource language (LRL) applications. These findings highlight the need for targeted domain adaptation techniques, adaptive routing strategies, and multilingual training frameworks for Akan and other LRLs.
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。
