Deep neural networks employing Multi-Task Learning and stacked bottleneck features for speech synthesis
Explore this paper's citation graph
- Type
- article
- Published
- 2015-04-19
- Cited by
- 270
- References
- 27
- Access
- Open access
- OpenAlex
- https://openalex.org/W1499332833
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:12016916
Keywords
Computer science, Bottleneck, Hidden Markov model, Speech recognition, Artificial neural network
References
- Combining a vector space representation of linguistic context with a deep neural network for text-to-speech synthesis
- Extracting deep bottleneck features using stacked auto-encoders
- Reformulating the HMM as a trajectory model by imposing explicit relationships between static and dynamic feature vector sequences
- Deep mixture density networks for acoustic modeling in statistical parametric speech synthesis
- A Speech Parameter Generation Algorithm Considering Global Variance for HMM-Based Speech Synthesis
- Modeling Spectral Envelopes Using Restricted Boltzmann Machines and Deep Belief Networks for Statistical Parametric Speech Synthesis
- Multi-distribution deep belief network for speech synthesis
- Restructuring speech representations using a pitch-adaptive time-frequency smoothing and an instantaneous-frequency-based F0 extraction: Possible role of a repetitive structure in sounds
- Measuring a decade of progress in Text-to-Speech
- Multi-task learning in deep neural networks for improved phoneme recognition
- Statistical parametric speech synthesis using deep neural networks
- Auto-encoder bottleneck features using deep belief networks
- Minimum Generation Error Training for HMM-Based Speech Synthesis
- A unified architecture for natural language processing: deep neural networks with multitask learning
- Improved Bottleneck Features Using Pretrained Deep Neural Networks
- Statistical Parametric Speech Synthesis
- On the training aspects of Deep Neural Network (DNN) for parametric TTS synthesis
- Unit selection in a concatenative speech synthesis system using a large speech database
- Speech parameter generation algorithms for HMM-based speech synthesis
- TTS synthesis with bidirectional LSTM based recurrent neural networks
Cited by
- DNN-based unit selection using frame-sized speech segments
- Deep neural network context embeddings for model selection in rich-context HMM synthesis
- Towards minimum perceptual error training for DNN-based speech synthesis
- Complementary tasks for context-dependent deep neural network acoustic models
- A deep bidirectional LSTM approach for video-realistic talking head
- Sentence-level control vectors for deep neural network speech synthesis
- Investigating gated recurrent neural networks for speech synthesis
- Open-Domain Name Error Detection using a Multi-Task RNN
- Improving Trajectory Modelling for DNN-Based Speech Synthesis by Using Stacked Bottleneck Features and Minimum Generation Error Training
- Multi-task learning for speech recognition: an overview
- Wavelet-based decomposition of F0 as a secondary task for DNN-based speech synthesis with multi-task learning
- Minimum trajectory error training for deep neural networks, combined with stacked bottleneck features
- Gating recurrent mixture density networks for acoustic modeling in statistical parametric speech synthesis
- Unsupervised speaker adaptation for DNN-based TTS synthesis
- Initial investigation of speech synthesis based on complex-valued neural networks
- Speaker and language factorization in DNN-based TTS synthesis
- From HMMS to DNNS: Where do the improvements come from?
- Fusion of multiple parameterisations for DNN-based sinusoidal speech synthesis with multi-task learning
- Robust TTS duration modelling using DNNS
- Deep neural network-guided unit selection synthesis
Related papers
- Comparison of bottleneck detection methods for AGV systems
- Simulation test bed for manufacturing analysis: comparison of bottleneck detection methods for AGV systems
- Data-driven approach for diagnostic analysis of dynamic bottlenecks in serial manufacturing systems
- Identification and characteristics analysis of bottlenecks on urban expressways based on floating car data
- TechWare: HMM-based speech synthesis resources [Best of the Web]
- Reducing over-smoothness in HMM-based speech synthesis using exemplar-based voice conversion
- Arabic Speech Synthesis Based on HMM