SC-MoE: Switch Conformer Mixture of Experts for Unified Streaming and Non-streaming Code-Switching ASR

In this work, we propose a Switch-Conformer-based MoE system named SC-MoE for unified streaming and non-streaming code-switching (CS) automatic speech recognition (ASR), where we design a streaming MoE layer consisting of three language experts, which correspond to Mandarin, English, and blank, respectively, and equipped with a language identification (LID) network with a Connectionist Temporal Classification (CTC) loss as a router in the encoder of SC-MoE to achieve a real-time streaming CS ASR system. To further utilize the language information embedded in text, we also incorporate MoE layers into the decoder of SC-MoE. In addition, we introduce routers into every MoE layer of the encoder and the decoder and achieve better recognition performance. Experimental results show that the SC-MoE significantly improves CS ASR performances over baseline with comparable computational efficiency.

The RoyalFlush Automatic Speech Diarization and Recognition System for In-Car Multi-Channel Automatic Speech Recognition Challenge

This paper presents our system submission for the In-Car Multi-Channel Automatic Speech Recognition (ICMC-ASR) Challenge, which focuses on speaker diarization and speech recognition in complex multi-speaker scenarios. To address these challenges, we develop end-to-end speaker diarization models that notably decrease the diarization error rate (DER) by 49.58\% compared to the official baseline on the development set. For speech recognition, we utilize self-supervised learning representations to train end-to-end ASR models. By integrating these models, we achieve a character error rate (CER) of 16.93\% on the track 1 evaluation set, and a concatenated minimum permutation character error rate (cpCER) of 25.88\% on the track 2 evaluation set.

A Deep Representation Learning-based Speech Enhancement Method Using Complex Convolution Recurrent Variational Autoencoder

Generally, the performance of deep neural networks (DNNs) heavily depends on the quality of data representation learning. Our preliminary work has emphasized the significance of deep representation learning (DRL) in the context of speech enhancement (SE) applications. Specifically, our initial SE algorithm employed a gated recurrent unit variational autoencoder (VAE) with a Gaussian distribution to enhance the performance of certain existing SE systems. Building upon our preliminary framework, this paper introduces a novel approach for SE using deep complex convolutional recurrent networks with a VAE (DCCRN-VAE). DCCRN-VAE assumes that the latent variables of signals follow complex Gaussian distributions that are modeled by DCCRN, as these distributions can better capture the behaviors of complex signals. Additionally, we propose the application of a residual loss in DCCRN-VAE to further improve the quality of the enhanced speech. {Compared to our preliminary work, DCCRN-VAE introduces a more sophisticated DCCRN structure and probability distribution for DRL. Furthermore, in comparison to DCCRN, DCCRN-VAE employs a more advanced DRL strategy. The experimental results demonstrate that the proposed SE algorithm outperforms both our preliminary SE framework and the state-of-the-art DCCRN SE method in terms of scale-invariant signal-to-distortion ratio, speech quality, and speech intelligibility.

LE-SSL-MOS: Self-Supervised Learning MOS Prediction with Listener Enhancement

Recently, researchers have shown an increasing interest in automatically predicting the subjective evaluation for speech synthesis systems. This prediction is a challenging task, especially on the out-of-domain test set. In this paper, we proposed a novel fusion model for MOS prediction that combines supervised and unsupervised approaches. In the supervised aspect, we developed an SSL-based predictor called LE-SSL-MOS. The LE-SSL-MOS utilizes pre-trained self-supervised learning models and further improves prediction accuracy by utilizing the opinion scores of each utterance in the listener enhancement branch. In the unsupervised aspect, two steps are contained: we fine-tuned the unit language model (ULM) using highly intelligible domain data to improve the correlation of an unsupervised metric - SpeechLMScore. Another is that we utilized ASR confidence as a new metric with the help of ensemble learning. To our knowledge, this is the first architecture that fuses supervised and unsupervised methods for MOS prediction. With these approaches, our experimental results on the VoiceMOS Challenge 2023 show that LE-SSL-MOS performs better than the baseline. Our fusion system achieved an absolute improvement of 13% over LE-SSL-MOS on the noisy and enhanced speech track. Our system ranked 1st and 2nd, respectively, in the French speech synthesis track and the challenge's noisy and enhanced speech track.

Advancing the study of Large-Scale Learning in Overlapped Speech Detection

Overlapped Speech Detection (OSD) is an important part of speech applications involving analysis of multi-party conversations. However, most of the existing OSD systems are trained and evaluated on specific dataset, which limits the application scenarios of these systems. To solve this problem, we conduct a study of large-scale learning (LSL) in OSD tasks and propose a general 16K single-channel OSD system. In our study, 522 hours of labeled audio in different languages and styles are collected and used as the large-scale dataset. Rigorous comparative experiments are designed and used to evaluate the effectiveness of LSL in OSD tasks and select the appropriate model of general OSD system. The results show that LSL can significantly improve the performance and robustness of OSD models, and the OSD model based on Conformer (CF-OSD) with LSL is currently the best 16K single-channel OSD system. Moreover, the CF-OSD with LSL establishes a state-of-the-art performance with an F1-score of 81.6% and 53.8% on Alimeeting test set and DIHARD II evaluation set, respectively.

Hybrid-Regressive Neural Machine Translation

In this work, we empirically confirm that non-autoregressive translation with an iterative refinement mechanism (IR-NAT) suffers from poor acceleration robustness because it is more sensitive to decoding batch size and computing device setting than autoregressive translation (AT). Inspired by it, we attempt to investigate how to combine the strengths of autoregressive and non-autoregressive translation paradigms better. To this end, we demonstrate through synthetic experiments that prompting a small number of AT's predictions can promote one-shot non-autoregressive translation to achieve the equivalent performance of IR-NAT. Following this line, we propose a new two-stage translation prototype called hybrid-regressive translation (HRT). Specifically, HRT first generates discontinuous sequences via autoregression (e.g., make a prediction every k tokens, k>1) and then fills in all previously skipped tokens at once in a non-autoregressive manner. We also propose a bag of techniques to effectively and efficiently train HRT without adding any model parameters. HRT achieves the state-of-the-art BLEU score of 28.49 on the WMT En-De task and is at least 1.5x faster than AT, regardless of batch size and device. In addition, another bonus of HRT is that it successfully inherits the good characteristics of AT in the deep-encoder-shallow-decoder architecture. Concretely, compared to the vanilla HRT with a 6-layer encoder and 6-layer decoder, the inference speed of HRT with a 12-layer encoder and 1-layer decoder is further doubled on both GPU and CPU without BLEU loss.

The Royalflush System for VoxCeleb Speaker Recognition Challenge 2022

In this technical report, we describe the Royalflush submissions for the VoxCeleb Speaker Recognition Challenge 2022 (VoxSRC-22). Our submissions contain track 1, which is for supervised speaker verification and track 3, which is for semi-supervised speaker verification. For track 1, we develop a powerful U-Net-based speaker embedding extractor with a symmetric architecture. The proposed system achieves 2.06% in EER and 0.1293 in MinDCF on the validation set. Compared with the state-of-the-art ECAPA-TDNN, it obtains a relative improvement of 20.7% in EER and 22.70% in MinDCF. For track 3, we employ the joint training of source domain supervision and target domain self-supervision to get a speaker embedding extractor. The subsequent clustering process can obtain target domain pseudo-speaker labels. We adapt the speaker embedding extractor using all source and target domain data in a supervised manner, where it can fully leverage both domain information. Moreover, clustering and supervised domain adaptation can be repeated until the performance converges on the validation set. Our final submission is a fusion of 10 models and achieves 7.75% EER and 0.3517 MinDCF on the validation set.

Royalflush Speaker Diarization System for ICASSP 2022 Multi-channel Multi-party Meeting Transcription Challenge

This paper describes the Royalflush speaker diarization system submitted to the Multi-channel Multi-party Meeting Transcription Challenge(M2MeT). Our system comprises speech enhancement, overlapped speech detection, speaker embedding extraction, speaker clustering, speech separation and system fusion. In this system, we made three contributions. First, we propose an architecture of combining the multi-channel and U-Net-based models, aiming at utilizing the benefits of these two individual architectures, for far-field overlapped speech detection. Second, in order to use overlapped speech detection model to help speaker diarization, a speech separation based overlapped speech handling approach, in which the speaker verification technique is further applied, is proposed. Third, we explore three speaker embedding methods, and obtained the state-of-the-art performance on the CNCeleb-E test set. With these proposals, our best individual system significantly reduces DER from 15.25% to 6.40%, and the fusion of four systems finally achieves a DER of 6.30% on the far-field Alimeeting evaluation set.

The RoyalFlush System of Speech Recognition for M2MeT Challenge

This paper describes our RoyalFlush system for the track of multi-speaker automatic speech recognition (ASR) in the M2MeT challenge. We adopted the serialized output training (SOT) based multi-speakers ASR system with large-scale simulation data. Firstly, we investigated a set of front-end methods, including multi-channel weighted predicted error (WPE), beamforming, speech separation, speech enhancement and so on, to process training, validation and test sets. But we only selected WPE and beamforming as our frontend methods according to their experimental results. Secondly, we made great efforts in the data augmentation for multi-speaker ASR, mainly including adding noise and reverberation, overlapped speech simulation, multi-channel speech simulation, speed perturbation, front-end processing, and so on, which brought us a great performance improvement. Finally, in order to make full use of the performance complementary of different model architecture, we trained the standard conformer based joint CTC/Attention (Conformer) and U2++ ASR model with a bidirectional attention decoder, a modification of Conformer, to fuse their results. Comparing with the official baseline system, our system got a 12.22% absolute Character Error Rate (CER) reduction on the validation set and 12.11% on the test set.