The quality of automatic speech recognition (ASR) is typically measured by
word error rate (WER). WER estimation is a task aiming to predict the WER of an
ASR system, given a speech utterance and a transcription. This task has gained
increasing attention while advanced ASR systems are trained on large amounts of
data. In this case, WER estimation becomes necessary in many scenarios, for
example, selecting training data with unknown transcription quality or
estimating the testing performance of an ASR system without ground truth
transcriptions. Facing large amounts of data, the computation efficiency of a
WER estimator becomes essential in practical applications. However, previous
works usually did not consider it as a priority. In this paper, a Fast WER
estimator (Fe-WER) using self-supervised learning representation (SSLR) is
introduced. The estimator is built upon SSLR aggregated by average pooling. The
results show that Fe-WER outperformed the e-WER3 baseline relatively by 19.69%
and 7.16% on Ted-Lium3 in both evaluation metrics of root mean square error and
Pearson correlation coefficient, respectively. Moreover, the estimation
weighted by duration was 10.43% when the target was 10.88%. Lastly, the
inference speed was about 4x in terms of a real-time factor.

通过自监督学习表征方法，引入了一种快速的语音识别错误率估计器（Fe-WER）。实验结果在 Ted-Lium3 数据集上以均方根误差和皮尔逊相关系数两个评估指标相对于 e-WER3 基线分别提高了 19.69% 和 7.16%，而通过时长加权的估计结果与目标值的差异为 10.43% 和 10.88%。此外，该估计器的推理速度相当于实时因子的 4 倍。

使用自监督表示快速估计语音和文本的错误率

Fast Word Error Rate Estimation Using Self-Supervised Representations  For Speech And Text

Neural speech separation has made remarkable progress and its integration
with automatic speech recognition (ASR) is an important direction towards
realizing multi-speaker ASR. This work provides an insightful investigation of
speech separation in reverberant and noisy-reverberant scenarios as an ASR
front-end. In detail, we explore multi-channel separation methods, mask-based
beamforming and complex spectral mapping, as well as the best features to use
in the ASR back-end model. We employ the recent self-supervised learning
representation (SSLR) as a feature and improve the recognition performance from
the case with filterbank features. To further improve multi-speaker recognition
performance, we present a carefully designed training strategy for integrating
speech separation and recognition with SSLR. The proposed integration using
TF-GridNet-based complex spectral mapping and WavLM-based SSLR achieves a 2.5%
word error rate in reverberant WHAMR! test set, significantly outperforming an
existing mask-based MVDR beamforming and filterbank integration (28.9%).

深度学习在语音分离方面的应用及其对多说话人语音识别的整合进行了深入研究，并提出了一种通过复杂谱映射和自监督学习表示进行的训练策略，从而在噪声和混响环境下显著提升多说话人语音识别性能。

探索自监督学习表征中的语音分离与识别集成

Exploring the Integration of Speech Separation and Recognition with  Self-Supervised Learning Representation

This work presents our end-to-end (E2E) automatic speech recognition (ASR)
model targetting at robust speech recognition, called Integraded speech
Recognition with enhanced speech Input for Self-supervised learning
representation (IRIS). Compared with conventional E2E ASR models, the proposed
E2E model integrates two important modules including a speech enhancement (SE)
module and a self-supervised learning representation (SSLR) module. The SE
module enhances the noisy speech. Then the SSLR module extracts features from
enhanced speech to be used for speech recognition (ASR). To train the proposed
model, we establish an efficient learning scheme. Evaluation results on the
monaural CHiME-4 task show that the IRIS model achieves the best performance
reported in the literature for the single-channel CHiME-4 benchmark (2.0% for
the real development and 3.9% for the real test) thanks to the powerful
pre-trained SSLR module and the fine-tuned SE module.

本文介绍了一种针对鲁棒语音识别的全自动语音识别模型 IRIS，该模型整合了语音增强模块和自监督学习表征模块，并在单通道 CHiME-4 测试中表现出最好的性能（开发集：2.0％，测试集：3.9％）。