This paper investigates the utilization of an end-to-end diarization model as post-processing of conventional clustering-based diarization. Clustering-based diarization methods partition frames into clusters of the number of speakers; thus, they typically cannot handle overlapping speech because each frame is assigned to one speaker. On the other hand, some end-to-end diarization methods can handle overlapping speech by treating the problem as multi-label classification. Although some methods can treat a flexible number of speakers, they do not perform well when the number of speakers is large. To compensate for each other's weakness, we propose to use a two-speaker end-to-end diarization method as post-processing of the results obtained by a clustering-based method. We iteratively select two speakers from the results and update the results of the two speakers to improve the overlapped region. Experimental results show that the proposed algorithm consistently improved the performance of the state-of-the-art methods across CALLHOME, AMI, and DIHARD II datasets.
We investigate segmenting and clustering speech into low-bitrate phone-like sequences without supervision. We specifically constrain pretrained self-supervised vector-quantized (VQ) neural networks so that blocks of contiguous feature vectors are assigned to the same code, thereby giving a variable-rate segmentation of the speech into discrete units. Two segmentation methods are considered. In the first, features are greedily merged until a prespecified number of segments are reached. The second uses dynamic programming to optimize a squared error with a penalty term to encourage fewer but longer segments. We show that these VQ segmentation methods can be used without alteration across a wide range of tasks: unsupervised phone segmentation, ABX phone discrimination, same-different word discrimination, and as inputs to a symbolic word segmentation algorithm. The penalized method generally performs best. While results are only comparable to the state-of-the-art in some cases, in all tasks a reasonable competing approach is outperformed at a substantially lower bitrate.
Language model pre-training has shown promising results in various downstream tasks. In this context, we introduce a cross-modal pre-trained language model, called Speech-Text BERT (ST-BERT), to tackle end-to-end spoken language understanding (E2E SLU) tasks. Taking phoneme posterior and subword-level text as an input, ST-BERT learns a contextualized cross-modal alignment via our two proposed pre-training tasks: Cross-modal Masked Language Modeling (CM-MLM) and Cross-modal Conditioned Language Modeling (CM-CLM). Experimental results on three benchmarks present that our approach is effective for various SLU datasets and shows a surprisingly marginal performance degradation even when 1% of the training data are available. Also, our method shows further SLU performance gain via domain-adaptive pre-training with domain-specific speech-text pair data.
Voice conversion (VC) is a task that transforms the source speaker's timbre, accent, and tones in audio into another one's while preserving the linguistic content. It is still a challenging work, especially in a one-shot setting. Auto-encoder-based VC methods disentangle the speaker and the content in input speech without given the speaker's identity, so these methods can further generalize to unseen speakers. The disentangle capability is achieved by vector quantization (VQ), adversarial training, or instance normalization (IN). However, the imperfect disentanglement may harm the quality of output speech. In this work, to further improve audio quality, we use the U-Net architecture within an auto-encoder-based VC system. We find that to leverage the U-Net architecture, a strong information bottleneck is necessary. The VQ-based method, which quantizes the latent vectors, can serve the purpose. The objective and the subjective evaluations show that the proposed method performs well in both audio naturalness and speaker similarity.
Speaker diarization is an essential step for processing multi-speaker audio. Although an end-to-end neural diarization (EEND) method achieved state-of-the-art performance, it is limited to a fixed number of speakers. In this paper, we solve this fixed number of speaker issue by a novel speaker-wise conditional inference method based on the probabilistic chain rule. In the proposed method, each speaker's speech activity is regarded as a single random variable, and is estimated sequentially conditioned on previously estimated other speakers' speech activities. Similar to other sequence-to-sequence models, the proposed method produces a variable number of speakers with a stop sequence condition. We evaluated the proposed method on multi-speaker audio recordings of a variable number of speakers. Experimental results show that the proposed method can correctly produce diarization results with a variable number of speakers and outperforms the state-of-the-art end-to-end speaker diarization methods in terms of diarization error rate.
Prosody is a rich information source in natural language, serving as a marker for phenomena such as contrast. In order to make this information available to downstream tasks, we need a way to detect prosodic events in speech. We propose a new model for pitch accent detection, inspired by the work of Stehwien et al. (2018), who presented a CNN-based model for this task. Our model makes greater use of context by using full utterances as input and adding an LSTM layer. We find that these innovations lead to an improvement from 87.5% to 88.7% accuracy on pitch accent detection on American English speech in the Boston University Radio News Corpus, a state-of-the-art result. We also find that a simple baseline that just predicts a pitch accent on every content word yields 82.2% accuracy, and we suggest that this is the appropriate baseline for this task. Finally, we conduct ablation tests that show pitch is the most important acoustic feature for this task and this corpus.
The physically impaired commonly have difficulties performing simple routine tasks without relying on other individuals who are not always readily available and thus make them strive for independence. While their impaired abilities can in many cases be augmented (to certain degrees) with the use of assistive technologies, there has been little attention to their applications in embodied AI with assistive technologies. This paper presents the modular framework, architecture, and design of the mid-fidelity prototype of MARVIN: an artificial-intelligence-powered robotic assistant designed to help the physically impaired in performing simple day-to-day tasks. The prototype features a trivial locomotion unit and also utilizes various state-of-the-art neural network architectures for specific modular components of the system. These components perform specialized functions, such as automatic speech recognition, object detection, natural language understanding, speech synthesis, etc. We also discuss the constraints, challenges encountered, potential future applications and improvements towards succeeding prototypes.
Deep learning yields great results across many fields, from speech recognition, image classification, to translation. But for each problem, getting a deep model to work well involves research into the architecture and a long period of tuning. We present a single model that yields good results on a number of problems spanning multiple domains. In particular, this single model is trained concurrently on ImageNet, multiple translation tasks, image captioning (COCO dataset), a speech recognition corpus, and an English parsing task. Our model architecture incorporates building blocks from multiple domains. It contains convolutional layers, an attention mechanism, and sparsely-gated layers. Each of these computational blocks is crucial for a subset of the tasks we train on. Interestingly, even if a block is not crucial for a task, we observe that adding it never hurts performance and in most cases improves it on all tasks. We also show that tasks with less data benefit largely from joint training with other tasks, while performance on large tasks degrades only slightly if at all.
A speaker cluster-based speaker adaptive training (SAT) method under deep neural network-hidden Markov model (DNN-HMM) framework is presented in this paper. During training, speakers that are acoustically adjacent to each other are hierarchically clustered using an i-vector based distance metric. DNNs with speaker dependent layers are then adaptively trained for each cluster of speakers. Before decoding starts, an unseen speaker in test set is matched to the closest speaker cluster through comparing i-vector based distances. The previously trained DNN of the matched speaker cluster is used for decoding utterances of the test speaker. The performance of the proposed method on a large vocabulary spontaneous speech recognition task is evaluated on a training set of with 1500 hours of speech, and a test set of 24 speakers with 1774 utterances. Comparing to a speaker independent DNN with a baseline word error rate of 11.6%, a relative 6.8% reduction in word error rate is observed from the proposed method.