To support machine learning of cross-language prosodic mappings and other ways to improve speech-to-speech translation, we present a protocol for collecting closely matched pairs of utterances across languages, a description of the resulting data collection, and some observations and musings. This report is intended for 1) people using the corpus, 2) people extending the corpus, and 3) people designing similar collections of bilingual dialog data.
In the past decade, advances in deep learning have resulted in breakthroughs in a variety of areas, including computer vision, natural language understanding, speech recognition, and reinforcement learning. Specialized, high-performing neural architectures are crucial to the success of deep learning in these areas. Neural architecture search (NAS), the process of automating the design of neural architectures for a given task, is an inevitable next step in automating machine learning and has already outpaced the best human-designed architectures on many tasks. In the past few years, research in NAS has been progressing rapidly, with over 1000 papers released since 2020 (Deng and Lindauer, 2021). In this survey, we provide an organized and comprehensive guide to neural architecture search. We give a taxonomy of search spaces, algorithms, and speedup techniques, and we discuss resources such as benchmarks, best practices, other surveys, and open-source libraries.
In the context of keyword spotting (KWS), the replacement of handcrafted speech features by learnable features has not yielded superior KWS performance. In this study, we demonstrate that filterbank learning outperforms handcrafted speech features for KWS whenever the number of filterbank channels is severely decreased. Reducing the number of channels might yield certain KWS performance drop, but also a substantial energy consumption reduction, which is key when deploying common always-on KWS on low-resource devices. Experimental results on a noisy version of the Google Speech Commands Dataset show that filterbank learning adapts to noise characteristics to provide a higher degree of robustness to noise, especially when dropout is integrated. Thus, switching from typically used 40-channel log-Mel features to 8-channel learned features leads to a relative KWS accuracy loss of only 3.5% while simultaneously achieving a 6.3x energy consumption reduction.
Training speech translation (ST) models requires large and high-quality datasets. MuST-C is one of the most widely used ST benchmark datasets. It contains around 400 hours of speech-transcript-translation data for each of the eight translation directions. This dataset passes several quality-control filters during creation. However, we find that MuST-C still suffers from three major quality issues: audio-text misalignment, inaccurate translation, and unnecessary speaker's name. What are the impacts of these data quality issues for model development and evaluation? In this paper, we propose an automatic method to fix or filter the above quality issues, using English-German (En-De) translation as an example. Our experiments show that ST models perform better on clean test sets, and the rank of proposed models remains consistent across different test sets. Besides, simply removing misaligned data points from the training set does not lead to a better ST model.
A large and growing amount of speech content in real-life scenarios is being recorded on common consumer devices in uncontrolled environments, resulting in degraded speech quality. Transforming such low-quality device-degraded speech into high-quality speech is a goal of speech enhancement (SE). This paper introduces a new speech dataset, DDS, to facilitate the research on SE. DDS provides aligned parallel recordings of high-quality speech (recorded in professional studios) and a number of versions of low-quality speech, producing approximately 2,000 hours speech data. The DDS dataset covers 27 realistic recording conditions by combining diverse acoustic environments and microphone devices, and each version of a condition consists of multiple recordings from six different microphone positions to simulate various signal-to-noise ratio (SNR) and reverberation levels. We also test several SE baseline systems on the DDS dataset and show the impact of recording diversity on performance.
We propose Guided-TTS 2, a diffusion-based generative model for high-quality adaptive TTS using untranscribed data. Guided-TTS 2 combines a speaker-conditional diffusion model with a speaker-dependent phoneme classifier for adaptive text-to-speech. We train the speaker-conditional diffusion model on large-scale untranscribed datasets for a classifier-free guidance method and further fine-tune the diffusion model on the reference speech of the target speaker for adaptation, which only takes 40 seconds. We demonstrate that Guided-TTS 2 shows comparable performance to high-quality single-speaker TTS baselines in terms of speech quality and speaker similarity with only a ten-second untranscribed data. We further show that Guided-TTS 2 outperforms adaptive TTS baselines on multi-speaker datasets even with a zero-shot adaptation setting. Guided-TTS 2 can adapt to a wide range of voices only using untranscribed speech, which enables adaptive TTS with the voice of non-human characters such as Gollum in \textit{"The Lord of the Rings"}.
To tackle the rising phenomenon of hate speech, efforts have been made towards data curation and analysis. When it comes to analysis of bias, previous work has focused predominantly on race. In our work, we further investigate bias in hate speech datasets along racial, gender and intersectional axes. We identify strong bias against African American English (AAE), masculine and AAE+Masculine tweets, which are annotated as disproportionately more hateful and offensive than from other demographics. We provide evidence that BERT-based models propagate this bias and show that balancing the training data for these protected attributes can lead to fairer models with regards to gender, but not race.
Despite the recent progress in speech emotion recognition (SER), state-of-the-art systems lack generalisation across different conditions. A key underlying reason for poor generalisation is the scarcity of emotion datasets, which is a significant roadblock to designing robust machine learning (ML) models. Recent works in SER focus on utilising multitask learning (MTL) methods to improve generalisation by learning shared representations. However, most of these studies propose MTL solutions with the requirement of meta labels for auxiliary tasks, which limits the training of SER systems. This paper proposes an MTL framework (MTL-AUG) that learns generalised representations from augmented data. We utilise augmentation-type classification and unsupervised reconstruction as auxiliary tasks, which allow training SER systems on augmented data without requiring any meta labels for auxiliary tasks. The semi-supervised nature of MTL-AUG allows for the exploitation of the abundant unlabelled data to further boost the performance of SER. We comprehensively evaluate the proposed framework in the following settings: (1) within corpus, (2) cross-corpus and cross-language, (3) noisy speech, (4) and adversarial attacks. Our evaluations using the widely used IEMOCAP, MSP-IMPROV, and EMODB datasets show improved results compared to existing state-of-the-art methods.
The vast majority of speech separation methods assume that the number of speakers is known in advance, hence they are specific to the number of speakers. By contrast, a more realistic and challenging task is to separate a mixture in which the number of speakers is unknown. This paper formulates the speech separation with the unknown number of speakers as a multi-pass source extraction problem and proposes a coarse-to-fine recursive speech separation method. This method comprises two stages, namely, recursive cue extraction and target speaker extraction. The recursive cue extraction stage determines how many computational iterations need to be performed and outputs a coarse cue speech by monitoring statistics in the mixture. As the number of recursive iterations increases, the accumulation of distortion eventually comes into the extracted speech and reminder. Therefore, in the second stage, we use a target speaker extraction network to extract a fine speech based on the coarse target cue and the original distortionless mixture. Experiments show that the proposed method archived state-of-the-art performance on the WSJ0 dataset with a different number of speakers. Furthermore, it generalizes well to an unseen large number of speakers.
We present an approach to imbuing expressivity in a synthesized voice by acquiring a thematic analysis of 10 interviews with vocal studies and performance experts to inform the design framework for a real-time, interactive vocal persona that would generate compelling and appropriate contextually-dependent expression. The resultant tone of voice is defined as a point existing within a continuous, contextually-dependent probability space. The inclusion of voice persona in synthesized voice can be significant in a broad range of applications. Of particular interest is the potential impact in augmentative and assistive communication (AAC) community. Finally, we conclude with an introduction to our ongoing research investigating the themes of vocal persona and how they may continue to inform proposed expressive speech synthesis design frameworks.