Conversational Text-to-Speech (TTS) aims to synthesis an utterance with the right linguistic and affective prosody in a conversational context. The correlation between the current utterance and the dialogue history at the utterance level was used to improve the expressiveness of synthesized speech. However, the fine-grained information in the dialogue history at the word level also has an important impact on the prosodic expression of an utterance, which has not been well studied in the prior work. Therefore, we propose a novel expressive conversational TTS model, termed as FCTalker, that learn the fine and coarse grained context dependency at the same time during speech generation. Specifically, the FCTalker includes fine and coarse grained encoders to exploit the word and utterance-level context dependency. To model the word-level dependencies between an utterance and its dialogue history, the fine-grained dialogue encoder is built on top of a dialogue BERT model. The experimental results show that the proposed method outperforms all baselines and generates more expressive speech that is contextually appropriate. We release the source code at: https://github.com/walker-hyf/FCTalker.
Multimodal emotion recognition leverages complementary information across modalities to gain performance. However, we cannot guarantee that the data of all modalities are always present in practice. In the studies to predict the missing data across modalities, the inherent difference between heterogeneous modalities, namely the modality gap, presents a challenge. To address this, we propose to use invariant features for a missing modality imagination network (IF-MMIN) which includes two novel mechanisms: 1) an invariant feature learning strategy that is based on the central moment discrepancy (CMD) distance under the full-modality scenario; 2) an invariant feature based imagination module (IF-IM) to alleviate the modality gap during the missing modalities prediction, thus improving the robustness of multimodal joint representation. Comprehensive experiments on the benchmark dataset IEMOCAP demonstrate that the proposed model outperforms all baselines and invariantly improves the overall emotion recognition performance under uncertain missing-modality conditions. We release the code at: https://github.com/ZhuoYulang/IF-MMIN.
Emotional voice conversion (EVC) aims to convert the emotional state of an utterance from one emotion to another while preserving the linguistic content and speaker identity. Current studies mostly focus on modelling the conversion between several specific emotion types. Synthesizing mixed effects of emotions could help us to better imitate human emotions, and facilitate more natural human-computer interaction. In this research, for the first time, we formulate and study the research problem of mixed emotion synthesis for EVC. We regard emotional styles as a series of emotion attributes that are learnt from a ranking-based support vector machine (SVM). Each attribute measures the degree of the relevance between the speech recordings belonging to different emotion types. We then incorporate those attributes into a sequence-to-sequence (seq2seq) emotional voice conversion framework. During the training, the framework not only learns to characterize the input emotional style, but also quantifies its relevance with other emotion types. At run-time, various emotional mixtures can be produced by manually defining the attributes. We conduct objective and subjective evaluations to validate our idea in terms of mixed emotion synthesis. We further build an emotion triangle as an application of emotion transition. Codes and speech samples are publicly available.
Spiking neural networks (SNNs) are shown to be more biologically plausible and energy efficient over their predecessors. However, there is a lack of an efficient and generalized training method for deep SNNs, especially for deployment on analog computing substrates. In this paper, we put forward a generalized learning rule, termed Local Tandem Learning (LTL). The LTL rule follows the teacher-student learning approach by mimicking the intermediate feature representations of a pre-trained ANN. By decoupling the learning of network layers and leveraging highly informative supervisor signals, we demonstrate rapid network convergence within five training epochs on the CIFAR-10 dataset while having low computational complexity. Our experimental results have also shown that the SNNs thus trained can achieve comparable accuracies to their teacher ANNs on CIFAR-10, CIFAR-100, and Tiny ImageNet datasets. Moreover, the proposed LTL rule is hardware friendly. It can be easily implemented on-chip to perform fast parameter calibration and provide robustness against the notorious device non-ideality issues. It, therefore, opens up a myriad of opportunities for training and deployment of SNN on ultra-low-power mixed-signal neuromorphic computing chips.10
Speech is the surface form of a finite set of phonetic units, which can be represented by discrete codes. We propose the Code BERT (CoBERT) approach for self-supervised speech representation learning. The idea is to convert an utterance to a sequence of discrete codes, and perform code representation learning, where we predict the code representations based on a masked view of the original speech input. Unlike the prior self-distillation approaches of which the teacher and the student are of the same modality, our target model predicts representations from a different modality. CoBERT outperforms the most recent state-of-the-art performance on the ASR task and brings significant improvements on the SUPERB speech translation (ST) task.
Output length is critical to dialogue summarization systems. The dialogue summary length is determined by multiple factors, including dialogue complexity, summary objective, and personal preferences. In this work, we approach dialogue summary length from three perspectives. First, we analyze the length differences between existing models' outputs and the corresponding human references and find that summarization models tend to produce more verbose summaries due to their pretraining objectives. Second, we identify salient features for summary length prediction by comparing different model settings. Third, we experiment with a length-aware summarizer and show notable improvement on existing models if summary length can be well incorporated. Analysis and experiments are conducted on popular DialogSum and SAMSum datasets to validate our findings.
This technical report describes our system for track 1, 2 and 4 of the VoxCeleb Speaker Recognition Challenge 2022 (VoxSRC-22). By combining several ResNet variants, our submission for track 1 attained a minDCF of 0:090 with EER 1:401%. By further incorporating three fine-tuned pre-trained models, our submission for track 2 achieved a minDCF of 0:072 with EER 1:119%. For track 4, our system consisted of voice activity detection (VAD), speaker embedding extraction, agglomerative hierarchical clustering (AHC) followed by a re-clustering step based on a Bayesian hidden Markov model and overlapped speech detection and handling. Our submission for track 4 achieved a diarisation error rate (DER) of 4.86%. The submissions all ranked the 2nd places for the corresponding tracks.
Accented text-to-speech (TTS) synthesis seeks to generate speech with an accent (L2) as a variant of the standard version (L1). Accented TTS synthesis is challenging as L2 is different from L1 in both in terms of phonetic rendering and prosody pattern. Furthermore, there is no easy solution to the control of the accent intensity in an utterance. In this work, we propose a neural TTS architecture, that allows us to control the accent and its intensity during inference. This is achieved through three novel mechanisms, 1) an accent variance adaptor to model the complex accent variance with three prosody controlling factors, namely pitch, energy and duration; 2) an accent intensity modeling strategy to quantify the accent intensity; 3) a consistency constraint module to encourage the TTS system to render the expected accent intensity at a fine level. Experiments show that the proposed system attains superior performance to the baseline models in terms of accent rendering and intensity control. To our best knowledge, this is the first study of accented TTS synthesis with explicit intensity control.
FFSVC2022 is the second challenge of far-field speaker verification. FFSVC2022 provides the fully-supervised far-field speaker verification to further explore the far-field scenario and proposes semi-supervised far-field speaker verification. In contrast to FFSVC2020, FFSVC2022 focus on the single-channel scenario. In addition, a supplementary set for the FFSVC2020 dataset is released this year. The supplementary set consists of more recording devices and has the same data distribution as the FFSVC2022 evaluation set. This paper summarizes the FFSVC 2022, including tasks description, trial designing details, a baseline system and a summary of challenge results. The challenge results indicate substantial progress made in the field but also present that there are still difficulties with the far-field scenario.
FFSVC2022 is the second challenge of far-field speaker verification. FFSVC2022 provides the fully-supervised far-field speaker verification to further explore the far-field scenario and proposes semi-supervised far-field speaker verification. In contrast to FFSVC2020, FFSVC2022 focus on the single-channel scenario. In addition, a supplementary set for the FFSVC2020 dataset is released this year. The supplementary set consists of more recording devices and has the same data distribution as the FFSVC2022 evaluation set. This paper summarizes the FFSVC 2022, including tasks description, trial designing details, a baseline system and a summary of challenge results. The challenge results indicate substantial progress made in the field but also present that there are still difficulties with the far-field scenario.