Recent developments in deep learning have led to a significant innovation in various classic and practical subjects, including speech recognition, computer vision, question answering, information retrieval and so on. In the context of natural language processing (NLP), language representations have shown giant successes in many downstream tasks, so the school of studies have become a major stream of research recently. Because the immenseness of multimedia data along with speech have spread around the world in our daily life, spoken document retrieval (SDR) has become an important research subject in the past decades. Targeting on enhancing the SDR performance, the paper concentrates on proposing a neural retrieval framework, which assembles the merits of using language modeling (LM) mechanism in SDR and leveraging the abstractive information learned by the language representation models. Consequently, to our knowledge, this is a pioneer study on supervised training of a neural LM-based SDR framework, especially combined with the pretrained language representation methods.
Voice conversion with deep neural networks has become extremely popular over the last few years with improvements over the past VC architectures. In particular, GAN architectures such as the cycleGAN and the VAEGAN have offered the possibility to learn voice conversion from non-parallel databases. However, GAN-based methods are highly unstable, requiring often a careful tuning of hyper-parameters, and can lead to poor voice identity conversion and substantially degraded converted speech signal. This paper discusses and tackles the stability issues of the GAN in the context of voice conversion. The proposed SoftGAN method aims at reducing the impact of the generator on the discriminator and vice versa during training, so both can learn more gradually and efficiently during training, in particular avoiding a training not in tandem. A subjective experiment conducted on a voice conversion task on the voice conversion challenge 2018 dataset shows that the proposed SoftGAN significantly improves the quality of the voice conversion while preserving the naturalness of the converted speech.
Neural TTS has shown it can generate high quality synthesized speech. In this paper, we investigate the multi-speaker latent space to improve neural TTS for adapting the system to new speakers with only several minutes of speech or enhancing a premium voice by utilizing the data from other speakers for richer contextual coverage and better generalization. A multi-speaker neural TTS model is built with the embedded speaker information in both spectral and speaker latent space. The experimental results show that, with less than 5 minutes of training data from a new speaker, the new model can achieve an MOS score of 4.16 in naturalness and 4.64 in speaker similarity close to human recordings (4.74). For a well-trained premium voice, we can achieve an MOS score of 4.5 for out-of-domain texts, which is comparable to an MOS of 4.58 for professional recordings, and significantly outperforms single speaker result of 4.28.
This paper proposes a speaker recognition (SRE) task with trivial speech events, such as cough and laugh. These trivial events are ubiquitous in conversations and less subjected to intentional change, therefore offering valuable particularities to discover the genuine speaker from disguised speech. However, trivial events are often short and idiocratic in spectral patterns, making SRE extremely difficult. Fortunately, we found a very powerful deep feature learning structure that can extract highly speaker-sensitive features. By employing this tool, we studied the SRE performance on three types of trivial events: cough, laugh and "Wei" (a short Chinese "Hello"). The results show that there is rich speaker information within these trivial events, even for cough that is intuitively less speaker distinguishable. With the deep feature approach, the EER can reach 10%-14% with the three trivial events, despite their extremely short durations (0.2-1.0 seconds).
In this paper, we propose dictionary attacks against speaker verification - a novel attack vector that aims to match a large fraction of speaker population by chance. We introduce a generic formulation of the attack that can be used with various speech representations and threat models. The attacker uses adversarial optimization to maximize raw similarity of speaker embeddings between a seed speech sample and a proxy population. The resulting master voice successfully matches a non-trivial fraction of people in an unknown population. Adversarial waveforms obtained with our approach can match on average 69% of females and 38% of males enrolled in the target system at a strict decision threshold calibrated to yield false alarm rate of 1%. By using the attack with a black-box voice cloning system, we obtain master voices that are effective in the most challenging conditions and transferable between speaker encoders. We also show that, combined with multiple attempts, this attack opens even more to serious issues on the security of these systems.
Speaker extraction aims to extract the target speaker's voice from a multi-talker speech mixture given an auxiliary reference utterance. Recent studies show that speaker extraction benefits from the location or direction of the target speaker. However, these studies assume that the target speaker's location is known in advance or detected by an extra visual cue, e.g., face image or video. In this paper, we propose an end-to-end localized target speaker extraction on pure speech cues, that is called L-SpEx. Specifically, we design a speaker localizer driven by the target speaker's embedding to extract the spatial features, including direction-of-arrival (DOA) of the target speaker and beamforming output. Then, the spatial cues and target speaker's embedding are both used to form a top-down auditory attention to the target speaker. Experiments on the multi-channel reverberant dataset called MC-Libri2Mix show that our L-SpEx approach significantly outperforms the baseline system.
Question answering (QA) systems are now available through numerous commercial applications for a wide variety of domains, serving millions of users that interact with them via speech interfaces. However, current benchmarks in QA research do not account for the errors that speech recognition models might introduce, nor do they consider the language variations (dialects) of the users. To address this gap, we augment an existing QA dataset to construct a multi-dialect, spoken QA benchmark on five languages (Arabic, Bengali, English, Kiswahili, Korean) with more than 68k audio prompts in 24 dialects from 255 speakers. We provide baseline results showcasing the real-world performance of QA systems and analyze the effect of language variety and other sensitive speaker attributes on downstream performance. Last, we study the fairness of the ASR and QA models with respect to the underlying user populations. The dataset, model outputs, and code for reproducing all our experiments are available: https://github.com/ffaisal93/SD-QA.
The Transformer model is widely used in natural language processing for sentence representation. However, the previous Transformer-based models focus on function words that have limited meaning in most cases and could merely extract high-level semantic abstraction features. In this paper, two approaches are introduced to improve the performance of Transformers. We calculated the attention score by multiplying the part-of-speech weight vector with the correlation coefficient, which helps extract the words with more practical meaning. The weight vector is obtained by the input text sequence based on the importance of the part-of-speech. Furthermore, we fuse the features of each layer to make the sentence representation results more comprehensive and accurate. In experiments, we demonstrate the effectiveness of our model Transformer-F on three standard text classification datasets. Experimental results show that our proposed model significantly boosts the performance of text classification as compared to the baseline model. Specifically, we obtain a 5.28% relative improvement over the vanilla Transformer on the simple tasks.
PanGEA, the Panoramic Graph Environment Annotation toolkit, is a lightweight toolkit for collecting speech and text annotations in photo-realistic 3D environments. PanGEA immerses annotators in a web-based simulation and allows them to move around easily as they speak and/or listen. It includes database and cloud storage integration, plus utilities for automatically aligning recorded speech with manual transcriptions and the virtual pose of the annotators. Out of the box, PanGEA supports two tasks -- collecting navigation instructions and navigation instruction following -- and it could be easily adapted for annotating walking tours, finding and labeling landmarks or objects, and similar tasks. We share best practices learned from using PanGEA in a 20,000 hour annotation effort to collect the Room-Across-Room dataset. We hope that our open-source annotation toolkit and insights will both expedite future data collection efforts and spur innovation on the kinds of grounded language tasks such environments can support.