Bayesian HMM clustering of x-vector sequences (VBx) has become a widely adopted diarization baseline model in publications and challenges. It uses an HMM to model speaker turns, a generatively trained probabilistic linear discriminant analysis (PLDA) for speaker distribution modeling, and Bayesian inference to estimate the assignment of x-vectors to speakers. This paper presents a new framework for updating the VBx parameters using discriminative training, which directly optimizes a predefined loss. We also propose a new loss that better correlates with the diarization error rate compared to binary cross-entropy $\unicode{x2013}$ the default choice for diarization end-to-end systems. Proof-of-concept results across three datasets (AMI, CALLHOME, and DIHARD II) demonstrate the method's capability of automatically finding hyperparameters, achieving comparable performance to those found by extensive grid search, which typically requires additional hyperparameter behavior knowledge. Moreover, we show that discriminative fine-tuning of PLDA can further improve the model's performance. We release the source code with this publication.
We propose a modular pipeline for the single-channel separation, recognition, and diarization of meeting-style recordings and evaluate it on the Libri-CSS dataset. Using a Continuous Speech Separation (CSS) system with a TF-GridNet separation architecture, followed by a speaker-agnostic speech recognizer, we achieve state-of-the-art recognition performance in terms of Optimal Reference Combination Word Error Rate (ORC WER). Then, a d-vector-based diarization module is employed to extract speaker embeddings from the enhanced signals and to assign the CSS outputs to the correct speaker. Here, we propose a syntactically informed diarization using sentence- and word-level boundaries of the ASR module to support speaker turn detection. This results in a state-of-the-art Concatenated minimum-Permutation Word Error Rate (cpWER) for the full meeting recognition pipeline.
This paper details our speaker diarization system designed for multi-domain, multi-microphone casual conversations. The proposed diarization pipeline uses weighted prediction error (WPE)-based dereverberation as a front end, then applies end-to-end neural diarization with vector clustering (EEND-VC) to each channel separately. It integrates the diarization result obtained from each channel using diarization output voting error reduction plus overlap (DOVER-LAP). To harness the knowledge from the target domain and results integrated across all channels, we apply self-supervised adaptation for each session by retraining the EEND-VC with pseudo-labels derived from DOVER-LAP. The proposed system was incorporated into NTT's submission for the distant automatic speech recognition task in the CHiME-7 challenge. Our system achieved 65 % and 62 % relative improvements on development and eval sets compared to the organizer-provided VC-based baseline diarization system, securing third place in diarization performance.
Diffusion model-based speech enhancement has received increased attention since it can generate very natural enhanced signals and generalizes well to unseen conditions. Diffusion models have been explored for several sub-tasks of speech enhancement, such as speech denoising, dereverberation, and source separation. In this paper, we investigate their use for target speech extraction (TSE), which consists of estimating the clean speech signal of a target speaker in a mixture of multi-talkers. TSE is realized by conditioning the extraction process on a clue identifying the target speaker. We show we can realize TSE using a conditional diffusion model conditioned on the clue. Besides, we introduce ensemble inference to reduce potential extraction errors caused by the diffusion process. In experiments on Libri2mix corpus, we show that the proposed diffusion model-based TSE combined with ensemble inference outperforms a comparable TSE system trained discriminatively.
MeetEval is an open-source toolkit to evaluate all kinds of meeting transcription systems. It provides a unified interface for the computation of commonly used Word Error Rates (WERs), specifically cpWER, ORC WER and MIMO WER along other WER definitions. We extend the cpWER computation by a temporal constraint to ensure that only words are identified as correct when the temporal alignment is plausible. This leads to a better quality of the matching of the hypothesis string to the reference string that more closely resembles the actual transcription quality, and a system is penalized if it provides poor time annotations. Since word-level timing information is often not available, we present a way to approximate exact word-level timings from segment-level timings (e.g., a sentence) and show that the approximation leads to a similar WER as a matching with exact word-level annotations. At the same time, the time constraint leads to a speedup of the matching algorithm, which outweighs the additional overhead caused by processing the time stamps.
Self-supervised learning (SSL) for speech representation has been successfully applied in various downstream tasks, such as speech and speaker recognition. More recently, speech SSL models have also been shown to be beneficial in advancing spoken language understanding tasks, implying that the SSL models have the potential to learn not only acoustic but also linguistic information. In this paper, we aim to clarify if speech SSL techniques can well capture linguistic knowledge. For this purpose, we introduce SpeechGLUE, a speech version of the General Language Understanding Evaluation (GLUE) benchmark. Since GLUE comprises a variety of natural language understanding tasks, SpeechGLUE can elucidate the degree of linguistic ability of speech SSL models. Experiments demonstrate that speech SSL models, although inferior to text-based SSL models, perform better than baselines, suggesting that they can acquire a certain amount of general linguistic knowledge from just unlabeled speech data.
End-to-end speech summarization (E2E SSum) directly summarizes input speech into easy-to-read short sentences with a single model. This approach is promising because it, in contrast to the conventional cascade approach, can utilize full acoustical information and mitigate to the propagation of transcription errors. However, due to the high cost of collecting speech-summary pairs, an E2E SSum model tends to suffer from training data scarcity and output unnatural sentences. To overcome this drawback, we propose for the first time to integrate a pre-trained language model (LM), which is highly capable of generating natural sentences, into the E2E SSum decoder via transfer learning. In addition, to reduce the gap between the independently pre-trained encoder and decoder, we also propose to transfer the baseline E2E SSum encoder instead of the commonly used automatic speech recognition encoder. Experimental results show that the proposed model outperforms baseline and data augmented models.
Neural transducer (RNNT)-based target-speaker speech recognition (TS-RNNT) directly transcribes a target speaker's voice from a multi-talker mixture. It is a promising approach for streaming applications because it does not incur the extra computation costs of a target speech extraction frontend, which is a critical barrier to quick response. TS-RNNT is trained end-to-end given the input speech (i.e., mixtures and enrollment speech) and reference transcriptions. The training mixtures are generally simulated by mixing single-talker signals, but conventional TS-RNNT training does not utilize single-speaker signals. This paper proposes using knowledge distillation (KD) to exploit the parallel mixture/single-talker speech data. Our proposed KD scheme uses an RNNT system pretrained with the target single-talker speech input to generate pseudo labels for the TS-RNNT training. Experimental results show that TS-RNNT systems trained with the proposed KD scheme outperform a baseline TS-RNNT.
Self-supervised learning (SSL) is the latest breakthrough in speech processing, especially for label-scarce downstream tasks by leveraging massive unlabeled audio data. The noise robustness of the SSL is one of the important challenges to expanding its application. We can use speech enhancement (SE) to tackle this issue. However, the mismatch between the SE model and SSL models potentially limits its effect. In this work, we propose a new SE training criterion that minimizes the distance between clean and enhanced signals in the feature representation of the SSL model to alleviate the mismatch. We expect that the loss in the SSL domain could guide SE training to preserve or enhance various levels of characteristics of the speech signals that may be required for high-level downstream tasks. Experiments show that our proposal improves the performance of an SE and SSL pipeline on five downstream tasks with noisy input while maintaining the SE performance.