Automated Speech Recognition shows superhuman performance for adult English
speech on a range of benchmarks, but disappoints when fed children's speech.
This has long sat in the way of child-robot interaction. Recent evolutions in
data-driven speech recognition, including the availability of Transformer
architectures and unprecedented volumes of training data, might mean a
breakthrough for child speech recognition and social robot applications aimed
at children. We revisit a study on child speech recognition from 2017 and show
that indeed performance has increased, with newcomer OpenAI Whisper doing
markedly better than leading commercial cloud services. While transcription is
not perfect yet, the best model recognises 60.3% of sentences correctly barring
small grammatical differences, with sub-second transcription time running on a
local GPU, showing potential for usable autonomous child-robot speech
interactions.

自动语音识别在成人英语语音方面显示出超人的表现，但在儿童语音方面表现不佳。最新的数据驱动语音识别技术包括 Transformer 架构和前所未有的训练数据量，可能会为儿童语音识别和面向儿童的社交机器人应用带来突破。我们重新审视了 2017 年的一项关于儿童语音识别的研究，并表明性能确实有所提高，新晋的 OpenAI Whisper 相比领先的商业云服务表现明显更好。尽管转录还不完美，但最佳模型可以正确识别 60.3% 的句子，除了一些小的语法差异，使用本地 GPU 运行的亚秒级转录时间显示出可用于自主儿童 - 机器人语音交互的潜力。

儿童在人机交互中的语音识别：问题解决了吗？

Child Speech Recognition in Human-Robot Interaction: Problem Solved?

Pre-training speech models on large volumes of data has achieved remarkable
success. OpenAI Whisper is a multilingual multitask model trained on 680k hours
of supervised speech data. It generalizes well to various speech recognition
and translation benchmarks even in a zero-shot setup. However, the full
pipeline for developing such models (from data collection to training) is not
publicly accessible, which makes it difficult for researchers to further
improve its performance and address training-related issues such as efficiency,
robustness, fairness, and bias. This work presents an Open Whisper-style Speech
Model (OWSM), which reproduces Whisper-style training using an open-source
toolkit and publicly available data. OWSM even supports more translation
directions and can be more efficient to train. We will publicly release all
scripts used for data preparation, training, inference, and scoring as well as
pre-trained models and training logs to promote open science.

使用开源工具包与公开可用的数据，本文提出了一种 Open Whisper-style Speech Model (OWSM) 来训练语音模型，以解决以前无法公开访问的全流程模型开发所面临的性能提升、效率、鲁棒性、公正性和偏见等问题，并公开发布所有脚本、预训练模型和训练日志，以促进开放科学。