Automatic methods to predict listener opinions of synthesized speech remain elusive since listeners, systems being evaluated, characteristics of the speech, and even the instructions given and the rating scale all vary from test to test. While automatic predictors for metrics such as mean opinion score (MOS) can achieve high prediction accuracy on samples from the same test, they typically fail to generalize well to new listening test contexts. In this paper, using a variety of networks for MOS prediction including MOSNet and self-supervised speech models such as wav2vec2, we investigate their performance on data from different listening tests in both zero-shot and fine-tuned settings. We find that wav2vec2 models fine-tuned for MOS prediction have good generalization capability to out-of-domain data even for the most challenging case of utterance-level predictions in the zero-shot setting, and that fine-tuning to in-domain data can improve predictions. We also observe that unseen systems are especially challenging for MOS prediction models.
This work explores the task of synthesizing speech in nonexistent human-sounding voices. We call this task "speaker generation", and present TacoSpawn, a system that performs competitively at this task. TacoSpawn is a recurrent attention-based text-to-speech model that learns a distribution over a speaker embedding space, which enables sampling of novel and diverse speakers. Our method is easy to implement, and does not require transfer learning from speaker ID systems. We present objective and subjective metrics for evaluating performance on this task, and demonstrate that our proposed objective metrics correlate with human perception of speaker similarity. Audio samples are available on our demo page.
Automatic Speech Recognition (ASR) is greatly developed in recent years, which expedites many applications on other fields. For the ASR research, speech corpus is always an essential foundation, especially for the vertical industry, such as Air Traffic Control (ATC). There are some speech corpora for common applications, public or paid. However, for the ATC, it is difficult to collect raw speeches from real systems due to safety issues. More importantly, for a supervised learning task like ASR, annotating the transcription is a more laborious work, which hugely restricts the prospect of ASR application. In this paper, a multilingual speech corpus (ATCSpeech) from real ATC systems, including accented Mandarin Chinese and English, is built and released to encourage the non-commercial ASR research in ATC domain. The corpus is detailly introduced from the perspective of data amount, speaker gender and role, speech quality and other attributions. In addition, the performance of our baseline ASR models is also reported. A community edition for our speech database can be applied and used under a special contrast. To our best knowledge, this is the first work that aims at building a real and multilingual ASR corpus for the air traffic related research.
Speech is understood better by using visual context; for this reason, there have been many attempts to use images to adapt automatic speech recognition (ASR) systems. Current work, however, has shown that visually adapted ASR models only use images as a regularization signal, while completely ignoring their semantic content. In this paper, we present a set of experiments where we show the utility of the visual modality under noisy conditions. Our results show that multimodal ASR models can recover words which are masked in the input acoustic signal, by grounding its transcriptions using the visual representations. We observe that integrating visual context can result in up to 35% relative improvement in masked word recovery. These results demonstrate that end-to-end multimodal ASR systems can become more robust to noise by leveraging the visual context.
Recent methods in speech and language technology pretrain very LARGE models which are fine-tuned for specific tasks. However, the benefits of such LARGE models are often limited to a few resource rich languages of the world. In this work, we make multiple contributions towards building ASR systems for low resource languages from the Indian subcontinent. First, we curate 17,000 hours of raw speech data for 40 Indian languages from a wide variety of domains including education, news, technology, and finance. Second, using this raw speech data we pretrain several variants of wav2vec style models for 40 Indian languages. Third, we analyze the pretrained models to find key features: codebook vectors of similar sounding phonemes are shared across languages, representations across layers are discriminative of the language family, and attention heads often pay attention within small local windows. Fourth, we fine-tune this model for downstream ASR for 9 languages and obtain state-of-the-art results on 3 public datasets, including on very low-resource languages such as Sinhala and Nepali. Our work establishes that multilingual pretraining is an effective strategy for building ASR systems for the linguistically diverse speakers of the Indian subcontinent.
Deep neural networks (DNNs) have achieved unprecedented success in the field of artificial intelligence (AI), including computer vision, natural language processing and speech recognition. However, their superior performance comes at the considerable cost of computational complexity, which greatly hinders their applications in many resource-constrained devices, such as mobile phones and Internet of Things (IoT) devices. Therefore, methods and techniques that are able to lift the efficiency bottleneck while preserving the high accuracy of DNNs are in great demand in order to enable numerous edge AI applications. This paper provides an overview of efficient deep learning methods, systems and applications. We start from introducing popular model compression methods, including pruning, factorization, quantization as well as compact model design. To reduce the large design cost of these manual solutions, we discuss the AutoML framework for each of them, such as neural architecture search (NAS) and automated pruning and quantization. We then cover efficient on-device training to enable user customization based on the local data on mobile devices. Apart from general acceleration techniques, we also showcase several task-specific accelerations for point cloud, video and natural language processing by exploiting their spatial sparsity and temporal/token redundancy. Finally, to support all these algorithmic advancements, we introduce the efficient deep learning system design from both software and hardware perspectives.
In a pipeline speech translation system, automatic speech recognition (ASR) system will transmit errors in recognition to the downstream machine translation (MT) system. A standard machine translation system is usually trained on parallel corpus composed of clean text and will perform poorly on text with recognition noise, a gap well known in speech translation community. In this paper, we propose a training architecture which aims at making a neural machine translation model more robust against speech recognition errors. Our approach addresses the encoder and the decoder simultaneously using adversarial learning and data augmentation, respectively. Experimental results on IWSLT2018 speech translation task show that our approach can bridge the gap between the ASR output and the MT input, outperforms the baseline by up to 2.83 BLEU on noisy ASR output, while maintaining close performance on clean text.
Recently, Transformer has gained success in automatic speech recognition (ASR) field. However, it is challenging to deploy a Transformer-based end-to-end (E2E) model for online speech recognition. In this paper, we propose the Transformer-based online CTC/attention E2E ASR architecture, which contains the chunk self-attention encoder (chunk-SAE) and the monotonic truncated attention (MTA) based self-attention decoder (SAD). Firstly, the chunk-SAE splits the speech into isolated chunks. To reduce the computational cost and improve the performance, we propose the state reuse chunk-SAE. Sencondly, the MTA based SAD truncates the speech features monotonically and performs attention on the truncated features. To support the online recognition, we integrate the state reuse chunk-SAE and the MTA based SAD into online CTC/attention architecture. We evaluate the proposed online models on the HKUST Mandarin ASR benchmark and achieve a 23.66% character error rate (CER) with a 320 ms latency. Our online model yields as little as $0.19\%$ absolute CER degradation compared with the offline baseline, and achieves significant improvement over our prior work on Long Short-Term Memory (LSTM) based online E2E models.
We propose a separation guided speaker diarization (SGSD) approach by fully utilizing a complementarity of speech separation and speaker clustering. Since the conventional clustering-based speaker diarization (CSD) approach cannot well handle overlapping speech segments, we investigate, in this study, separation-based speaker diarization (SSD) which inherently has the potential to handle the speaker overlap regions. Our preliminary analysis shows that the state-of-the-art Conv-TasNet based speech separation, which works quite well on the simulation data, is unstable in realistic conversational speech due to the high mismatch speaking styles in simulated training speech and read speech. In doing so, separation-based processing can assist CSD in handling the overlapping speech segments under the realistic mismatched conditions. Specifically, several strategies are designed to select between the results of SSD and CSD systems based on an analysis of the instability of the SSD system performances. Experiments on the conversational telephone speech (CTS) data from DIHARD-III Challenge show that the proposed SGSD system can significantly improve the performance of state-of-the-art CSD systems, yielding relative diarization error rate reductions of 20.2% and 20.8% on the development set and evaluation set, respectively.
This survey presents a review of state-of-the-art deep neural network architectures, algorithms, and systems in vision and speech applications. Recent advances in deep artificial neural network algorithms and architectures have spurred rapid innovation and development of intelligent vision and speech systems. With availability of vast amounts of sensor data and cloud computing for processing and training of deep neural networks, and with increased sophistication in mobile and embedded technology, the next-generation intelligent systems are poised to revolutionize personal and commercial computing. This survey begins by providing background and evolution of some of the most successful deep learning models for intelligent vision and speech systems to date. An overview of large-scale industrial research and development efforts is provided to emphasize future trends and prospects of intelligent vision and speech systems. Robust and efficient intelligent systems demand low-latency and high fidelity in resource constrained hardware platforms such as mobile devices, robots, and automobiles. Therefore, this survey also provides a summary of key challenges and recent successes in running deep neural networks on hardware-restricted platforms, i.e. within limited memory, battery life, and processing capabilities. Finally, emerging applications of vision and speech across disciplines such as affective computing, intelligent transportation, and precision medicine are discussed. To our knowledge, this paper provides one of the most comprehensive surveys on the latest developments in intelligent vision and speech applications from the perspectives of both software and hardware systems. Many of these emerging technologies using deep neural networks show tremendous promise to revolutionize research and development for future vision and speech systems.