RA-CLAP: Relation-Augmented Emotional Speaking Style Contrastive Language-Audio Pretraining For Speech Retrieval

The Contrastive Language-Audio Pretraining (CLAP) model has demonstrated excellent performance in general audio description-related tasks, such as audio retrieval. However, in the emerging field of emotional speaking style description (ESSD), cross-modal contrastive pretraining remains largely unexplored. In this paper, we propose a novel speech retrieval task called emotional speaking style retrieval (ESSR), and ESS-CLAP, an emotional speaking style CLAP model tailored for learning relationship between speech and natural language descriptions. In addition, we further propose relation-augmented CLAP (RA-CLAP) to address the limitation of traditional methods that assume a strict binary relationship between caption and audio. The model leverages self-distillation to learn the potential local matching relationships between speech and descriptions, thereby enhancing generalization ability. The experimental results validate the effectiveness of RA-CLAP, providing valuable reference in ESSD.

Learning Emotion-Invariant Speaker Representations for Speaker Verification

In recent years, the rapid progress in speaker verification (SV) technology has been driven by the extraction of speaker representations based on deep learning. However, such representations are still vulnerable to emotion variability. To address this issue, we propose multiple improvements to train speaker encoders to increase emotion robustness. Firstly, we utilize CopyPaste-based data augmentation to gather additional parallel data, which includes different emotional expressions from the same speaker. Secondly, we apply cosine similarity loss to restrict parallel sample pairs and minimize intra-class variation of speaker representations to reduce their correlation with emotional information. Finally, we use emotion-aware masking (EM) based on the speech signal energy on the input parallel samples to further strengthen the speaker representation and make it emotion-invariant. We conduct a comprehensive ablation study to demonstrate the effectiveness of these various components. Experimental results show that our proposed method achieves a relative 19.29\% drop in EER compared to the baseline system.

Discrete Audio Representations for Automated Audio Captioning

Discrete audio representations, termed audio tokens, are broadly categorized into semantic and acoustic tokens, typically generated through unsupervised tokenization of continuous audio representations. However, their applicability to automated audio captioning (AAC) remains underexplored. This paper systematically investigates the viability of audio token-driven models for AAC through comparative analyses of various tokenization methods. Our findings reveal that audio tokenization leads to performance degradation in AAC models compared to those that directly utilize continuous audio representations. To address this issue, we introduce a supervised audio tokenizer trained with an audio tagging objective. Unlike unsupervised tokenizers, which lack explicit semantic understanding, the proposed tokenizer effectively captures audio event information. Experiments conducted on the Clotho dataset demonstrate that the proposed audio tokens outperform conventional audio tokens in the AAC task.

A Semantic Information-based Hierarchical Speech Enhancement Method Using Factorized Codec and Diffusion Model

Most current speech enhancement (SE) methods recover clean speech from noisy inputs by directly estimating time-frequency masks or spectrums. However, these approaches often neglect the distinct attributes, such as semantic content and acoustic details, inherent in speech signals, which can hinder performance in downstream tasks. Moreover, their effectiveness tends to degrade in complex acoustic environments. To overcome these challenges, we propose a novel, semantic information-based, step-by-step factorized SE method using factorized codec and diffusion model. Unlike traditional SE methods, our hierarchical modeling of semantic and acoustic attributes enables more robust clean speech recovery, particularly in challenging acoustic scenarios. Moreover, this method offers further advantages for downstream TTS tasks. Experimental results demonstrate that our algorithm not only outperforms SOTA baselines in terms of speech quality but also enhances TTS performance in noisy environments.

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.