Leveraging In-the-Wild Data for Effective Self-Supervised Pretraining in Speaker Recognition

Current speaker recognition systems primarily rely on supervised approaches, constrained by the scale of labeled datasets. To boost the system performance, researchers leverage large pretrained models such as WavLM to transfer learned high-level features to the downstream speaker recognition task. However, this approach introduces extra parameters as the pretrained model remains in the inference stage. Another group of researchers directly apply self-supervised methods such as DINO to speaker embedding learning, yet they have not explored its potential on large-scale in-the-wild datasets. In this paper, we present the effectiveness of DINO training on the large-scale WenetSpeech dataset and its transferability in enhancing the supervised system performance on the CNCeleb dataset. Additionally, we introduce a confidence-based data filtering algorithm to remove unreliable data from the pretraining dataset, leading to better performance with less training data. The associated pretrained models, confidence files, pretraining and finetuning scripts will be made available in the Wespeaker toolkit.

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/.

Attention-based Encoder-Decoder End-to-End Neural Diarization with Embedding Enhancer

Deep neural network-based systems have significantly improved the performance of speaker diarization tasks. However, end-to-end neural diarization (EEND) systems often struggle to generalize to scenarios with an unseen number of speakers, while target speaker voice activity detection (TS-VAD) systems tend to be overly complex. In this paper, we propose a simple attention-based encoder-decoder network for end-to-end neural diarization (AED-EEND). In our training process, we introduce a teacher-forcing strategy to address the speaker permutation problem, leading to faster model convergence. For evaluation, we propose an iterative decoding method that outputs diarization results for each speaker sequentially. Additionally, we propose an Enhancer module to enhance the frame-level speaker embeddings, enabling the model to handle scenarios with an unseen number of speakers. We also explore replacing the transformer encoder with a Conformer architecture, which better models local information. Furthermore, we discovered that commonly used simulation datasets for speaker diarization have a much higher overlap ratio compared to real data. We found that using simulated training data that is more consistent with real data can achieve an improvement in consistency. Extensive experimental validation demonstrates the effectiveness of our proposed methodologies. Our best system achieved a new state-of-the-art diarization error rate (DER) performance on all the CALLHOME (10.08%), DIHARD II (24.64%), and AMI (13.00%) evaluation benchmarks, when no oracle voice activity detection (VAD) is used. Beyond speaker diarization, our AED-EEND system also shows remarkable competitiveness as a speech type detection model.

InstructME: An Instruction Guided Music Edit And Remix Framework with Latent Diffusion Models

Music editing primarily entails the modification of instrument tracks or remixing in the whole, which offers a novel reinterpretation of the original piece through a series of operations. These music processing methods hold immense potential across various applications but demand substantial expertise. Prior methodologies, although effective for image and audio modifications, falter when directly applied to music. This is attributed to music's distinctive data nature, where such methods can inadvertently compromise the intrinsic harmony and coherence of music. In this paper, we develop InstructME, an Instruction guided Music Editing and remixing framework based on latent diffusion models. Our framework fortifies the U-Net with multi-scale aggregation in order to maintain consistency before and after editing. In addition, we introduce chord progression matrix as condition information and incorporate it in the semantic space to improve melodic harmony while editing. For accommodating extended musical pieces, InstructME employs a chunk transformer, enabling it to discern long-term temporal dependencies within music sequences. We tested InstructME in instrument-editing, remixing, and multi-round editing. Both subjective and objective evaluations indicate that our proposed method significantly surpasses preceding systems in music quality, text relevance and harmony. Demo samples are available at https://musicedit.github.io/

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

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%).

Exploring Binary Classification Loss For Speaker Verification

The mismatch between close-set training and open-set testing usually leads to significant performance degradation for speaker verification task. For existing loss functions, metric learning-based objectives depend strongly on searching effective pairs which might hinder further improvements. And popular multi-classification methods are usually observed with degradation when evaluated on unseen speakers. In this work, we introduce SphereFace2 framework which uses several binary classifiers to train the speaker model in a pair-wise manner instead of performing multi-classification. Benefiting from this learning paradigm, it can efficiently alleviate the gap between training and evaluation. Experiments conducted on Voxceleb show that the SphereFace2 outperforms other existing loss functions, especially on hard trials. Besides, large margin fine-tuning strategy is proven to be compatible with it for further improvements. Finally, SphereFace2 also shows its strong robustness to class-wise noisy labels which has the potential to be applied in the semi-supervised training scenario with inaccurate estimated pseudo labels. Codes are available in https://github.com/Hunterhuan/sphereface2_speaker_verification

Adapting Multi-Lingual ASR Models for Handling Multiple Talkers

State-of-the-art large-scale universal speech models (USMs) show a decent automatic speech recognition (ASR) performance across multiple domains and languages. However, it remains a challenge for these models to recognize overlapped speech, which is often seen in meeting conversations. We propose an approach to adapt USMs for multi-talker ASR. We first develop an enhanced version of serialized output training to jointly perform multi-talker ASR and utterance timestamp prediction. That is, we predict the ASR hypotheses for all speakers, count the speakers, and estimate the utterance timestamps at the same time. We further introduce a lightweight adapter module to maintain the multilingual property of the USMs even when we perform the adaptation with only a single language. Experimental results obtained using the AMI and AliMeeting corpora show that our proposed approach effectively transfers the USMs to a strong multilingual multi-talker ASR model with timestamp prediction capability.

Weakly-Supervised Speech Pre-training: A Case Study on Target Speech Recognition

Self-supervised learning (SSL) based speech pre-training has attracted much attention for its capability of extracting rich representations learned from massive unlabeled data. On the other hand, the use of weakly-supervised data is less explored for speech pre-training. To fill this gap, we propose a weakly-supervised speech pre-training method based on speaker-aware speech data. It adopts a similar training procedure to the widely-used masked speech prediction based SSL framework, while incorporating additional target-speaker enrollment information as an auxiliary input. In this way, the learned representation is steered towards the target speaker even in the presence of highly overlapping interference, allowing potential applications to tasks such as target speech recognition. Our experiments on Libri2Mix and WSJ0-2mix datasets show that the proposed model achieves significantly better ASR performance compared to WavLM, the state-of-the-art SSL model with denoising capability.

Whisper-KDQ: A Lightweight Whisper via Guided Knowledge Distillation and Quantization for Efficient ASR

Due to the rapid development of computing hardware resources and the dramatic growth of data, pre-trained models in speech recognition, such as Whisper, have significantly improved the performance of speech recognition tasks. However, these models usually have a high computational overhead, making it difficult to execute effectively on resource-constrained devices. To speed up inference and reduce model size while maintaining performance, we propose a novel guided knowledge distillation and quantization for large pre-trained model Whisper. The student model selects distillation and quantization layers based on quantization loss and distillation loss, respectively. We compressed $\text{Whisper}_\text{small}$ to $\text{Whisper}_\text{base}$ and $\text{Whisper}_\text{tiny}$ levels, making $\text{Whisper}_\text{small}$ 5.18x/10.48x smaller, respectively. Moreover, compared to the original $\text{Whisper}_\text{base}$ and $\text{Whisper}_\text{tiny}$, there is also a relative character error rate~(CER) reduction of 11.3% and 14.0% for the new compressed model respectively.