No abstract

This paper presents an investigation of speaker adaptation using a continuous vocoder for parametric text-to-speech (TTS) synthesis. In purposes that demand low computational complexity, conventional vocoder-based statistical parametric speech synthesis can be preferable. While capable of remarkable naturalness, recent neural vocoders nonetheless fall short of the criteria for real-time synthesis. We investigate our former continuous vocoder, in which the excitation is characterized employing two one-dimensional parameters: Maximum Voiced Frequency and continuous fundamental frequency (F0). We show that an average voice can be trained for deep neural network-based TTS utilizing data from nine English speakers. We did speaker adaptation experiments for each target speaker with 400 utterances (approximately 14 minutes). We showed an apparent enhancement in the quality and naturalness of synthesized speech compared to our previous work by utilizing the recurrent neural network topologies. According to the objective studies (Mel-Cepstral Distortion and F0 correlation), the quality of speaker adaptation using Continuous Vocoder-based DNN-TTS is slightly better than the WORLD Vocoder-based baseline. The subjective MUSHRA-like test results also showed that our speaker adaptation technique is almost as natural as the WORLD vocoder using Gated Recurrent Unit and Long Short Term Memory networks. The proposed vocoder, being capable of real-time synthesis, can be used for applications which need fast synthesis speed.

The Industry 4.0 initiative has been showing the way for industrial production to optimize operations based on collecting, processing, and sharing data. There are new requirements on the production floor: flexible but ultra-reliable, low latency wireless communications through interoperable systems can share data. Further challenges of data sharing and storage arise when diverse systems come into play at the Manufacturing Operations Management and Business Planning & Logistics levels. The emerging complex cyber-physical systems of systems need to be engineered with care. Regarding industrial requirements, the telecommunication industry has many similarities to production—including ultra-reliability, high complexity, and having humans “in-the-loop”. The current paper aims to provide an overview of converging telco-grade solutions that can be successfully applied in the wide sense of industrial production. These toolsets range from model-driven engineering through system interoperability frameworks, 5G- and 6G-supported manufacturing, and the telco-cloud to speech recognition in noisy environments.

No abstract

Speech synthesis has the aim of generating humanlike speech from text. Nowadays, with end-to-end systems, highly natural synthesized speech can be achieved if a large enough dataset is available from the target speaker. However, often it would be necessary to adapt to a target speaker for whom only a few training samples are available. Limited data speaker adaptation might be a difficult problem due to the overly few training samples. Issues might appear with a limited speaker dataset, such as the irregular allocation of linguistic tokens (i.e., some speech sounds are left out from the synthesized speech). To build lightweight systems, measuring the number of minimum data samples and training epochs is crucial to acquire a reasonable quality. We conducted detailed experiments with four target speakers for adaptive speaker text-to-speech (TTS) synthesis to show the performance of the end-to-end Tacotron2 model and the WaveGlow neural vocoder with an English dataset at several training data samples and training lengths. According to our investigation of objective and subjective evaluations, the Tacotron2 model exhibits good performance in terms of speech quality and similarity for unseen target speakers at 100 sentences of data (pair of text and audio) with a relatively low training time.