Abstract:Obtaining high-quality speaker embeddings in multi-speaker conditions is crucial for many applications. A recently proposed guided speaker embedding framework, which utilizes speech activities of target and non-target speakers as clues, drastically improved embeddings under severe overlap with small degradation in low-overlap cases. However, since extreme overlaps are rare in natural conversations, this degradation cannot be overlooked. This paper first reveals that the degradation is caused by the global-statistics-based modules, widely used in speaker embedding extractors, being overly sensitive to intervals containing only non-target speakers. As a countermeasure, we propose an extension of such modules that exploit the target speaker activity clues, to compute statistics from intervals where the target is active. The proposed method improves speaker verification performance in both low and high overlap ratios, and diarization performance on multiple datasets.
Abstract:End-to-End Neural Diarization with Vector Clustering is a powerful and practical approach to perform Speaker Diarization. Multiple enhancements have been proposed for the segmentation model of these pipelines, but their synergy had not been thoroughly evaluated. In this work, we provide an in-depth analysis on the impact of major architecture choices on the performance of the pipeline. We investigate different encoders (SincNet, pretrained and finetuned WavLM), different decoders (LSTM, Mamba, and Conformer), different losses (multilabel and multiclass powerset), and different chunk sizes. Through in-depth experiments covering nine datasets, we found that the finetuned WavLM-based encoder always results in the best systems by a wide margin. The LSTM decoder is outclassed by Mamba- and Conformer-based decoders, and while we found Mamba more robust to other architecture choices, it is slightly inferior to our best architecture, which uses a Conformer encoder. We found that multilabel and multiclass powerset losses do not have the same distribution of errors. We confirmed that the multiclass loss helps almost all models attain superior performance, except when finetuning WavLM, in which case, multilabel is the superior choice. We also evaluated the impact of the chunk size on all aforementioned architecture choices and found that newer architectures tend to better handle long chunk sizes, which can greatly improve pipeline performance. Our best system achieved state-of-the-art results on five widely used speaker diarization datasets.
Abstract:End-to-end speaker diarization enables accurate overlap-aware diarization by jointly estimating multiple speakers' speech activities in parallel. This approach is data-hungry, requiring a large amount of labeled conversational data, which cannot be fully obtained from real datasets alone. To address this issue, large-scale simulated data is often used for pretraining, but it requires enormous storage and I/O capacity, and simulating data that closely resembles real conversations remains challenging. In this paper, we propose pretraining a model to identify multiple speakers from an input fully overlapped mixture as an alternative to pretraining a diarization model. This method eliminates the need to prepare a large-scale simulated dataset while leveraging large-scale speaker recognition datasets for training. Through comprehensive experiments, we demonstrate that the proposed method enables a highly accurate yet lightweight local diarization model without simulated conversational data.
Abstract:This paper proposes a guided speaker embedding extraction system, which extracts speaker embeddings of the target speaker using speech activities of target and interference speakers as clues. Several methods for long-form overlapped multi-speaker audio processing are typically two-staged: i) segment-level processing and ii) inter-segment speaker matching. Speaker embeddings are often used for the latter purpose. Typical speaker embedding extraction approaches only use single-speaker intervals to avoid corrupting the embeddings with speech from interference speakers. However, this often makes speaker embeddings impossible to extract because sufficiently long non-overlapping intervals are not always available. In this paper, we propose using speaker activities as clues to extract the embedding of the speaker-of-interest directly from overlapping speech. Specifically, we concatenate the activity of target and non-target speakers to acoustic features before being fed to the model. We also condition the attention weights used for pooling so that the attention weights of the intervals in which the target speaker is inactive are zero. The effectiveness of the proposed method is demonstrated in speaker verification and speaker diarization.
Abstract:Mamba is a newly proposed architecture which behaves like a recurrent neural network (RNN) with attention-like capabilities. These properties are promising for speaker diarization, as attention-based models have unsuitable memory requirements for long-form audio, and traditional RNN capabilities are too limited. In this paper, we propose to assess the potential of Mamba for diarization by comparing the state-of-the-art neural segmentation of the pyannote pipeline with our proposed Mamba-based variant. Mamba's stronger processing capabilities allow usage of longer local windows, which significantly improve diarization quality by making the speaker embedding extraction more reliable. We find Mamba to be a superior alternative to both traditional RNN and the tested attention-based model. Our proposed Mamba-based system achieves state-of-the-art performance on three widely used diarization datasets.
Abstract:We present a distant automatic speech recognition (DASR) system developed for the CHiME-8 DASR track. It consists of a diarization first pipeline. For diarization, we use end-to-end diarization with vector clustering (EEND-VC) followed by target speaker voice activity detection (TS-VAD) refinement. To deal with various numbers of speakers, we developed a new multi-channel speaker counting approach. We then apply guided source separation (GSS) with several improvements to the baseline system. Finally, we perform ASR using a combination of systems built from strong pre-trained models. Our proposed system achieves a macro tcpWER of 21.3 % on the dev set, which is a 57 % relative improvement over the baseline.
Abstract:This paper proposes a method for extracting speaker embedding for each speaker from a variable-length recording containing multiple speakers. Speaker embeddings are crucial not only for speaker recognition but also for various multi-speaker speech applications such as speaker diarization and target-speaker speech processing. Despite the challenges of obtaining a single speaker's speech without pre-registration in multi-speaker scenarios, most studies on speaker embedding extraction focus on extracting embeddings only from single-speaker recordings. Some methods have been proposed for extracting speaker embeddings directly from multi-speaker recordings, but they typically require preparing a model for each possible number of speakers or involve complicated training procedures. The proposed method computes the embeddings of multiple speakers by focusing on different parts of the frame-wise embeddings extracted from the input multi-speaker audio. This is achieved by recursively computing attention weights for pooling the frame-wise embeddings. Additionally, we propose using the calculated attention weights to estimate the number of speakers in the recording, which allows the same model to be applied to various numbers of speakers. Experimental evaluations demonstrate the effectiveness of the proposed method in speaker verification and diarization tasks.
Abstract:Real-time target speaker extraction (TSE) is intended to extract the desired speaker's voice from the observed mixture of multiple speakers in a streaming manner. Implementing real-time TSE is challenging as the computational complexity must be reduced to provide real-time operation. This work introduces to Conv-TasNet-based TSE a new architecture based on state space modeling (SSM) that has been shown to model long-term dependency effectively. Owing to SSM, fewer dilated convolutional layers are required to capture temporal dependency in Conv-TasNet, resulting in the reduction of model complexity. We also enlarge the window length and shift of the convolutional (TasNet) frontend encoder to reduce the computational cost further; the performance decline is compensated by over-parameterization of the frontend encoder. The proposed method reduces the real-time factor by 78% from the conventional causal Conv-TasNet-based TSE while matching its performance.
Abstract:This paper presents a novel speaking-style captioning method that generates diverse descriptions while accurately predicting speaking-style information. Conventional learning criteria directly use original captions that contain not only speaking-style factor terms but also syntax words, which disturbs learning speaking-style information. To solve this problem, we introduce factor-conditioned captioning (FCC), which first outputs a phrase representing speaking-style factors (e.g., gender, pitch, etc.), and then generates a caption to ensure the model explicitly learns speaking-style factors. We also propose greedy-then-sampling (GtS) decoding, which first predicts speaking-style factors deterministically to guarantee semantic accuracy, and then generates a caption based on factor-conditioned sampling to ensure diversity. Experiments show that FCC outperforms the original caption-based training, and with GtS, it generates more diverse captions while keeping style prediction performance.
Abstract:This paper proposes a speech rhythm-based method for speaker embeddings to model phoneme duration using a few utterances by the target speaker. Speech rhythm is one of the essential factors among speaker characteristics, along with acoustic features such as F0, for reproducing individual utterances in speech synthesis. A novel feature of the proposed method is the rhythm-based embeddings extracted from phonemes and their durations, which are known to be related to speaking rhythm. They are extracted with a speaker identification model similar to the conventional spectral feature-based one. We conducted three experiments, speaker embeddings generation, speech synthesis with generated embeddings, and embedding space analysis, to evaluate the performance. The proposed method demonstrated a moderate speaker identification performance (15.2% EER), even with only phonemes and their duration information. The objective and subjective evaluation results demonstrated that the proposed method can synthesize speech with speech rhythm closer to the target speaker than the conventional method. We also visualized the embeddings to evaluate the relationship between the distance of the embeddings and the perceptual similarity. The visualization of the embedding space and the relation analysis between the closeness indicated that the distribution of embeddings reflects the subjective and objective similarity.