CoVoMix: Advancing Zero-Shot Speech Generation for Human-like Multi-talker Conversations

Recent advancements in zero-shot text-to-speech (TTS) modeling have led to significant strides in generating high-fidelity and diverse speech. However, dialogue generation, along with achieving human-like naturalness in speech, continues to be a challenge in the field. In this paper, we introduce CoVoMix: Conversational Voice Mixture Generation, a novel model for zero-shot, human-like, multi-speaker, multi-round dialogue speech generation. CoVoMix is capable of first converting dialogue text into multiple streams of discrete tokens, with each token stream representing semantic information for individual talkers. These token streams are then fed into a flow-matching based acoustic model to generate mixed mel-spectrograms. Finally, the speech waveforms are produced using a HiFi-GAN model. Furthermore, we devise a comprehensive set of metrics for measuring the effectiveness of dialogue modeling and generation. Our experimental results show that CoVoMix can generate dialogues that are not only human-like in their naturalness and coherence but also involve multiple talkers engaging in multiple rounds of conversation. These dialogues, generated within a single channel, are characterized by seamless speech transitions, including overlapping speech, and appropriate paralinguistic behaviors such as laughter. Audio samples are available at https://aka.ms/covomix.

Profile-Error-Tolerant Target-Speaker Voice Activity Detection

Target-Speaker Voice Activity Detection (TS-VAD) utilizes a set of speaker profiles alongside an input audio signal to perform speaker diarization. While its superiority over conventional methods has been demonstrated, the method can suffer from errors in speaker profiles, as those profiles are typically obtained by running a traditional clustering-based diarization method over the input signal. This paper proposes an extension to TS-VAD, called Profile-Error-Tolerant TS-VAD (PET-TSVAD), which is robust to such speaker profile errors. This is achieved by employing transformer-based TS-VAD that can handle a variable number of speakers and further introducing a set of additional pseudo-speaker profiles to handle speakers undetected during the first pass diarization. During training, we use speaker profiles estimated by multiple different clustering algorithms to reduce the mismatch between the training and testing conditions regarding speaker profiles. Experimental results show that PET-TSVAD consistently outperforms the existing TS-VAD method on both the VoxConverse and DIHARD-I datasets.

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.

Target Sound Extraction with Variable Cross-modality Clues

Automatic target sound extraction (TSE) is a machine learning approach to mimic the human auditory perception capability of attending to a sound source of interest from a mixture of sources. It often uses a model conditioned on a fixed form of target sound clues, such as a sound class label, which limits the ways in which users can interact with the model to specify the target sounds. To leverage variable number of clues cross modalities available in the inference phase, including a video, a sound event class, and a text caption, we propose a unified transformer-based TSE model architecture, where a multi-clue attention module integrates all the clues across the modalities. Since there is no off-the-shelf benchmark to evaluate our proposed approach, we build a dataset based on public corpora, Audioset and AudioCaps. Experimental results for seen and unseen target-sound evaluation sets show that our proposed TSE model can effectively deal with a varying number of clues which improves the TSE performance and robustness against partially compromised clues.

Target Speaker Voice Activity Detection with Transformers and Its Integration with End-to-End Neural Diarization

This paper describes a speaker diarization model based on target speaker voice activity detection (TS-VAD) using transformers. To overcome the original TS-VAD model's drawback of being unable to handle an arbitrary number of speakers, we investigate model architectures that use input tensors with variable-length time and speaker dimensions. Transformer layers are applied to the speaker axis to make the model output insensitive to the order of the speaker profiles provided to the TS-VAD model. Time-wise sequential layers are interspersed between these speaker-wise transformer layers to allow the temporal and cross-speaker correlations of the input speech signal to be captured. We also extend a diarization model based on end-to-end neural diarization with encoder-decoder based attractors (EEND-EDA) by replacing its dot-product-based speaker detection layer with the transformer-based TS-VAD. Experimental results on VoxConverse show that using the transformers for the cross-speaker modeling reduces the diarization error rate (DER) of TS-VAD by 10.9%, achieving a new state-of-the-art (SOTA) DER of 4.74%. Also, our extended EEND-EDA reduces DER by 6.9% on the CALLHOME dataset relative to the original EEND-EDA with a similar model size, achieving a new SOTA DER of 11.18% under a widely used training data setting.

Leveraging Real Conversational Data for Multi-Channel Continuous Speech Separation

Existing multi-channel continuous speech separation (CSS) models are heavily dependent on supervised data - either simulated data which causes data mismatch between the training and real-data testing, or the real transcribed overlapping data, which is difficult to be acquired, hindering further improvements in the conversational/meeting transcription tasks. In this paper, we propose a three-stage training scheme for the CSS model that can leverage both supervised data and extra large-scale unsupervised real-world conversational data. The scheme consists of two conventional training approaches -- pre-training using simulated data and ASR-loss-based training using transcribed data -- and a novel continuous semi-supervised training between the two, in which the CSS model is further trained by using real data based on the teacher-student learning framework. We apply this scheme to an array-geometry-agnostic CSS model, which can use the multi-channel data collected from any microphone array. Large-scale meeting transcription experiments are carried out on both Microsoft internal meeting data and the AMI meeting corpus. The steady improvement by each training stage has been observed, showing the effect of the proposed method that enables leveraging real conversational data for CSS model training.

PickNet: Real-Time Channel Selection for Ad Hoc Microphone Arrays

This paper proposes PickNet, a neural network model for real-time channel selection for an ad hoc microphone array consisting of multiple recording devices like cell phones. Assuming at most one person to be vocally active at each time point, PickNet identifies the device that is spatially closest to the active person for each time frame by using a short spectral patch of just hundreds of milliseconds. The model is applied to every time frame, and the short time frame signals from the selected microphones are concatenated across the frames to produce an output signal. As the personal devices are usually held close to their owners, the output signal is expected to have higher signal-to-noise and direct-to-reverberation ratios on average than the input signals. Since PickNet utilizes only limited acoustic context at each time frame, the system using the proposed model works in real time and is robust to changes in acoustic conditions. Speech recognition-based evaluation was carried out by using real conversational recordings obtained with various smartphones. The proposed model yielded significant gains in word error rate with limited computational cost over systems using a block-online beamformer and a single distant microphone.

VarArray: Array-Geometry-Agnostic Continuous Speech Separation

Continuous speech separation using a microphone array was shown to be promising in dealing with the speech overlap problem in natural conversation transcription. This paper proposes VarArray, an array-geometry-agnostic speech separation neural network model. The proposed model is applicable to any number of microphones without retraining while leveraging the nonlinear correlation between the input channels. The proposed method adapts different elements that were proposed before separately, including transform-average-concatenate, conformer speech separation, and inter-channel phase differences, and combines them in an efficient and cohesive way. Large-scale evaluation was performed with two real meeting transcription tasks by using a fully developed transcription system requiring no prior knowledge such as reference segmentations, which allowed us to measure the impact that the continuous speech separation system could have in realistic settings. The proposed model outperformed a previous approach to array-geometry-agnostic modeling for all of the geometry configurations considered, achieving asclite-based speaker-agnostic word error rates of 17.5% and 20.4% for the AMI development and evaluation sets, respectively, in the end-to-end setting using no ground-truth segmentations.

All-neural beamformer for continuous speech separation

Continuous speech separation (CSS) aims to separate overlapping voices from a continuous influx of conversational audio containing an unknown number of utterances spoken by an unknown number of speakers. A common application scenario is transcribing a meeting conversation recorded by a microphone array. Prior studies explored various deep learning models for time-frequency mask estimation, followed by a minimum variance distortionless response (MVDR) filter to improve the automatic speech recognition (ASR) accuracy. The performance of these methods is fundamentally upper-bounded by MVDR's spatial selectivity. Recently, the all deep learning MVDR (ADL-MVDR) model was proposed for neural beamforming and demonstrated superior performance in a target speech extraction task using pre-segmented input. In this paper, we further adapt ADL-MVDR to the CSS task with several enhancements to enable end-to-end neural beamforming. The proposed system achieves significant word error rate reduction over a baseline spectral masking system on the LibriCSS dataset. Moreover, the proposed neural beamformer is shown to be comparable to a state-of-the-art MVDR-based system in real meeting transcription tasks, including AMI, while showing potentials to further simplify the runtime implementation and reduce the system latency with frame-wise processing.