Spoken Question Answering (SQA) is essential for machines to reply to user's
question by finding the answer span within a given spoken passage. SQA has been
previously achieved without ASR to avoid recognition errors and
Out-of-Vocabulary (OOV) problems. However, the real-world problem of
Open-domain SQA (openSQA), in which the machine needs to first retrieve
passages that possibly contain the answer from a spoken archive in addition,
was never considered. This paper proposes the first known end-to-end framework,
Speech Dense Passage Retriever (SpeechDPR), for the retrieval component of the
openSQA problem. SpeechDPR learns a sentence-level semantic representation by
distilling knowledge from the cascading model of unsupervised ASR (UASR) and
text dense retriever (TDR). No manually transcribed speech data is needed.
Initial experiments showed performance comparable to the cascading model of
UASR and TDR, and significantly better when UASR was poor, verifying this
approach is more robust to speech recognition errors.

提出基于语音密集检索器 (SpeechDPR) 的端到端框架，用于 Open-domain SQA 问题的检索组件，通过从无监督 ASR (UASR) 和文本密集检索器 (TDR) 的级联模型中提取知识来学习句子级语义表示，初步实验表明该方法在语音识别错误较大时表现更为鲁棒。

SpeechDPR: 开放领域口语问答的端到端口语段落检索

SpeechDPR: End-to-End Spoken Passage Retrieval for Open-Domain Spoken  Question Answering

This paper describes the ESPnet Unsupervised ASR Open-source Toolkit (EURO),
an end-to-end open-source toolkit for unsupervised automatic speech recognition
(UASR). EURO adopts the state-of-the-art UASR learning method introduced by the
Wav2vec-U, originally implemented at FAIRSEQ, which leverages self-supervised
speech representations and adversarial training. In addition to wav2vec2, EURO
extends the functionality and promotes reproducibility for UASR tasks by
integrating S3PRL and k2, resulting in flexible frontends from 27
self-supervised models and various graph-based decoding strategies. EURO is
implemented in ESPnet and follows its unified pipeline to provide UASR recipes
with a complete setup. This improves the pipeline's efficiency and allows EURO
to be easily applied to existing datasets in ESPnet. Extensive experiments on
three mainstream self-supervised models demonstrate the toolkit's effectiveness
and achieve state-of-the-art UASR performance on TIMIT and LibriSpeech
datasets. EURO will be publicly available at this https URL,
aiming to promote this exciting and emerging research area based on UASR
through open-source activity.

本文描述了 ESPnet Unsupervised ASR Open-source Toolkit (EURO)，这是一个用于无监督自动语音识别 (UASR) 的端到端开源工具包，它采用了 Wav2vec-U 的最先进的学习方法，综合 27 个自我监督模型和各种基于图形的解码策略。EURO 通过对 ESPnet 的现有数据集进行完整的设置，提高了流水线的效率，并在 TIMIT 和 LibriSpeech 数据集上取得了最先进的 UASR 性能。