SA-WavLM: Speaker-Aware Self-Supervised Pre-training for Mixture Speech

It was shown that pre-trained models with self-supervised learning (SSL) techniques are effective in various downstream speech tasks. However, most such models are trained on single-speaker speech data, limiting their effectiveness in mixture speech. This motivates us to explore pre-training on mixture speech. This work presents SA-WavLM, a novel pre-trained model for mixture speech. Specifically, SA-WavLM follows an "extract-merge-predict" pipeline in which the representations of each speaker in the input mixture are first extracted individually and then merged before the final prediction. In this pipeline, SA-WavLM performs speaker-informed extractions with the consideration of the interactions between different speakers. Furthermore, a speaker shuffling strategy is proposed to enhance the robustness towards the speaker absence. Experiments show that SA-WavLM either matches or improves upon the state-of-the-art pre-trained models.

Music-PAW: Learning Music Representations via Hierarchical Part-whole Interaction and Contrast

The excellent performance of recent self-supervised learning methods on various downstream tasks has attracted great attention from academia and industry. Some recent research efforts have been devoted to self-supervised music representation learning. Nevertheless, most of them learn to represent equally-sized music clips in the waveform or a spectrogram. Despite being effective in some tasks, learning music representations in such a manner largely neglect the inherent part-whole hierarchies of music. Due to the hierarchical nature of the auditory cortex [24], understanding the bottom-up structure of music, i.e., how different parts constitute the whole at different levels, is essential for music understanding and representation learning. This work pursues hierarchical music representation learning and introduces the Music-PAW framework, which enables feature interactions of cropped music clips with part-whole hierarchies. From a technical perspective, we propose a transformer-based part-whole interaction module to progressively reason the structural relationships between part-whole music clips at adjacent levels. Besides, to create a multi-hierarchy representation space, we devise a hierarchical contrastive learning objective to align part-whole music representations in adjacent hierarchies. The merits of audio representation learning from part-whole hierarchies have been validated on various downstream tasks, including music classification (single-label and multi-label), cover song identification and acoustic scene classification.

Prompt-driven Target Speech Diarization

We introduce a novel task named `target speech diarization', which seeks to determine `when target event occurred' within an audio signal. We devise a neural architecture called Prompt-driven Target Speech Diarization (PTSD), that works with diverse prompts that specify the target speech events of interest. We train and evaluate PTSD using sim2spk, sim3spk and sim4spk datasets, which are derived from the Librispeech. We show that the proposed framework accurately localizes target speech events. Furthermore, our framework exhibits versatility through its impressive performance in three diarization-related tasks: target speaker voice activity detection, overlapped speech detection and gender diarization. In particular, PTSD achieves comparable performance to specialized models across these tasks on both real and simulated data. This work serves as a reference benchmark and provides valuable insights into prompt-driven target speech processing.

USED: Universal Speaker Extraction and Diarization

Speaker extraction and diarization are two crucial enabling techniques for speech applications. Speaker extraction aims to extract a target speaker's voice from a multi-talk mixture, while speaker diarization demarcates speech segments by speaker, identifying `who spoke when'. The previous studies have typically treated the two tasks independently. However, the two tasks share a similar objective, that is to disentangle the speakers in the spectral domain for the former but in the temporal domain for the latter. It is logical to believe that the speaker turns obtained from speaker diarization can benefit speaker extraction, while the extracted speech offers more accurate speaker turns than the mixture speech. In this paper, we propose a unified framework called Universal Speaker Extraction and Diarization (USED). We extend the existing speaker extraction model to simultaneously extract the waveforms of all speakers. We also employ a scenario-aware differentiated loss function to address the problem of sparsely overlapped speech in real-world conversations. We show that the USED model significantly outperforms the baselines for both speaker extraction and diarization tasks, in both highly overlapped and sparsely overlapped scenarios. Audio samples are available at https://ajyy.github.io/demo/USED/.

DisCover: Disentangled Music Representation Learning for Cover Song Identification

In the field of music information retrieval (MIR), cover song identification (CSI) is a challenging task that aims to identify cover versions of a query song from a massive collection. Existing works still suffer from high intra-song variances and inter-song correlations, due to the entangled nature of version-specific and version-invariant factors in their modeling. In this work, we set the goal of disentangling version-specific and version-invariant factors, which could make it easier for the model to learn invariant music representations for unseen query songs. We analyze the CSI task in a disentanglement view with the causal graph technique, and identify the intra-version and inter-version effects biasing the invariant learning. To block these effects, we propose the disentangled music representation learning framework (DisCover) for CSI. DisCover consists of two critical components: (1) Knowledge-guided Disentanglement Module (KDM) and (2) Gradient-based Adversarial Disentanglement Module (GADM), which block intra-version and inter-version biased effects, respectively. KDM minimizes the mutual information between the learned representations and version-variant factors that are identified with prior domain knowledge. GADM identifies version-variant factors by simulating the representation transitions between intra-song versions, and exploits adversarial distillation for effect blocking. Extensive comparisons with best-performing methods and in-depth analysis demonstrate the effectiveness of DisCover and the and necessity of disentanglement for CSI.

CorrectSpeech: A Fully Automated System for Speech Correction and Accent Reduction

This study extends our previous work on text-based speech editing to developing a fully automated system for speech correction and accent reduction. Consider the application scenario that a recorded speech audio contains certain errors, e.g., inappropriate words, mispronunciations, that need to be corrected. The proposed system, named CorrectSpeech, performs the correction in three steps: recognizing the recorded speech and converting it into time-stamped symbol sequence, aligning recognized symbol sequence with target text to determine locations and types of required edit operations, and generating the corrected speech. Experiments show that the quality and naturalness of corrected speech depend on the performance of speech recognition and alignment modules, as well as the granularity level of editing operations. The proposed system is evaluated on two corpora: a manually perturbed version of VCTK and L2-ARCTIC. The results demonstrate that our system is able to correct mispronunciation and reduce accent in speech recordings. Audio samples are available online for demonstration https://daxintan-cuhk.github.io/CorrectSpeech/ .

Reducing language context confusion for end-to-end code-switching automatic speech recognition

Code-switching is about dealing with alternative languages in the communication process. Training end-to-end (E2E) automatic speech recognition (ASR) systems for code-switching is known to be a challenging problem because of the lack of data compounded by the increased language context confusion due to the presence of more than one language. In this paper, we propose a language-related attention mechanism to reduce multilingual context confusion for the E2E code-switching ASR model based on the Equivalence Constraint Theory (EC). The linguistic theory requires that any monolingual fragment that occurs in the code-switching sentence must occur in one of the monolingual sentences. It establishes a bridge between monolingual data and code-switching data. By calculating the respective attention of multiple languages, our method can efficiently transfer language knowledge from rich monolingual data. We evaluate our method on ASRU 2019 Mandarin-English code-switching challenge dataset. Compared with the baseline model, the proposed method achieves 11.37% relative mix error rate reduction.

CCA-MDD: A Coupled Cross-Attention based Framework for Streaming Mispronunciation detection and diagnosis

End-to-end models are becoming popular approaches for mispronunciation detection and diagnosis (MDD). A streaming MDD framework which is demanded by many practical applications still remains a challenge. This paper proposes a streaming end-to-end MDD framework called CCA-MDD. CCA-MDD supports online processing and is able to run strictly in real-time. The encoder of CCA-MDD consists of a conv-Transformer network based streaming acoustic encoder and an improved cross-attention named coupled cross-attention (CCA). The coupled cross-attention integrates encoded acoustic features with pre-encoded linguistic features. An ensemble of decoders trained from multi-task learning is applied for final MDD decision. Experiments on publicly available corpora demonstrate that CCA-MDD achieves comparable performance to published offline end-to-end MDD models.

EditSpeech: A Text Based Speech Editing System Using Partial Inference and Bidirectional Fusion

This paper presents the design, implementation and evaluation of a speech editing system, named EditSpeech, which allows a user to perform deletion, insertion and replacement of words in a given speech utterance, without causing audible degradation in speech quality and naturalness. The EditSpeech system is developed upon a neural text-to-speech (NTTS) synthesis framework. Partial inference and bidirectional fusion are proposed to effectively incorporate the contextual information related to the edited region and achieve smooth transition at both left and right boundaries. Distortion introduced to the unmodified parts of the utterance is alleviated. The EditSpeech system is developed and evaluated on English and Chinese in multi-speaker scenarios. Objective and subjective evaluation demonstrate that EditSpeech outperforms a few baseline systems in terms of low spectral distortion and preferred speech quality. Audio samples are available online for demonstration https://daxintan-cuhk.github.io/EditSpeech/ .

VQMIVC: Vector Quantization and Mutual Information-Based Unsupervised Speech Representation Disentanglement for One-shot Voice Conversion

One-shot voice conversion (VC), which performs conversion across arbitrary speakers with only a single target-speaker utterance for reference, can be effectively achieved by speech representation disentanglement. Existing work generally ignores the correlation between different speech representations during training, which causes leakage of content information into the speaker representation and thus degrades VC performance. To alleviate this issue, we employ vector quantization (VQ) for content encoding and introduce mutual information (MI) as the correlation metric during training, to achieve proper disentanglement of content, speaker and pitch representations, by reducing their inter-dependencies in an unsupervised manner. Experimental results reflect the superiority of the proposed method in learning effective disentangled speech representations for retaining source linguistic content and intonation variations, while capturing target speaker characteristics. In doing so, the proposed approach achieves higher speech naturalness and speaker similarity than current state-of-the-art one-shot VC systems. Our code, pre-trained models and demo are available at https://github.com/Wendison/VQMIVC.