Enrico Zovato

Giovanni Morrone, Samuele Cornell, Luca Serafini et al. · cmu

Recent works show that speech separation guided diarization (SSGD) is an increasingly promising direction, mainly thanks to the recent progress in speech separation. It performs diarization by first separating the speakers and then applying voice activity detection (VAD) on each separated stream. In this work we conduct an in-depth study of SSGD in the conversational telephone speech (CTS) domain, focusing mainly on low-latency streaming diarization applications. We consider three state-of-the-art speech separation (SSep) algorithms and study their performance both in online and offline scenarios, considering non-causal and causal implementations as well as continuous SSep (CSS) windowed inference. We compare different SSGD algorithms on two widely used CTS datasets: CALLHOME and Fisher Corpus (Part 1 and 2) and evaluate both separation and diarization performance. To improve performance, a novel, causal and computationally efficient leakage removal algorithm is proposed, which significantly decreases false alarms. We also explore, for the first time, fully end-to-end SSGD integration between SSep and VAD modules. Crucially, this enables fine-tuning on real-world data for which oracle speakers sources are not available. In particular, our best model achieves 8.8% DER on CALLHOME, which outperforms the current state-of-the-art end-to-end neural diarization model, despite being trained on an order of magnitude less data and having significantly lower latency, i.e., 0.1 vs. 1 s. Finally, we also show that the separated signals can be readily used also for automatic speech recognition, reaching performance close to using oracle sources in some configurations.

Martina Valente, Fabio Brugnara, Giovanni Morrone et al.

This paper addresses spoken language identification (SLI) and speech recognition of multilingual broadcast and institutional speech, real application scenarios that have been rarely addressed in the SLI literature. Observing that in these domains language changes are mostly associated with speaker changes, we propose a cascaded system consisting of speaker diarization and language identification and compare it with more traditional language identification and language diarization systems. Results show that the proposed system often achieves lower language classification and language diarization error rates (up to 10% relative language diarization error reduction and 60% relative language confusion reduction) and leads to lower WERs on multilingual test sets (more than 8% relative WER reduction), while at the same time does not negatively affect speech recognition on monolingual audio (with an absolute WER increase between 0.1% and 0.7% w.r.t. monolingual ASR).

Giuseppe Ruggiero, Enrico Zovato, Luigi Di Caro et al.

Deep learning models are becoming predominant in many fields of machine learning. Text-to-Speech (TTS), the process of synthesizing artificial speech from text, is no exception. To this end, a deep neural network is usually trained using a corpus of several hours of recorded speech from a single speaker. Trying to produce the voice of a speaker other than the one learned is expensive and requires large effort since it is necessary to record a new dataset and retrain the model. This is the main reason why the TTS models are usually single speaker. The proposed approach has the goal to overcome these limitations trying to obtain a system which is able to model a multi-speaker acoustic space. This allows the generation of speech audio similar to the voice of different target speakers, even if they were not observed during the training phase.