• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2004.11a
• /
• pp.317-322
• /
• 2004

In this paper, It was describe the processes of development of HiFi speaker system. Woofer and tweeter were fabricated by unskilled students and their 1.5 parameters were identified by known mass method. Based on T-S parameters port enclosure was designed and built by means of software. Acoustic radiation phenomena of port enclosure were simulated and compared to test result. Acoustic pressure difference between lower frequency and higher frequency was flattened by adopting optimal crossover network. Finally, built HiFi speaker system was showed good sound quality and sound pressure and electrical impedance was well agreed with test results each other.

• Phonetics and Speech Sciences
• /
• v.16 no.1
• /
• pp.67-76
• /
• 2024

Recent advances in text-to-speech (TTS) technology have significantly improved the quality of synthesized speech, reaching a level where it can closely imitate natural human speech. Especially, TTS models offering various voice characteristics and personalized speech, are widely utilized in fields such as artificial intelligence (AI) tutors, advertising, and video dubbing. Accordingly, in this paper, we propose a one-shot multi-speaker TTS system that can ensure acoustic diversity and synthesize personalized voice by generating speech using unseen target speakers' utterances. The proposed model integrates a speaker encoder into a TTS model consisting of the FastSpeech2 acoustic model and the HiFi-GAN vocoder. The speaker encoder, based on the pre-trained RawNet3, extracts speaker-specific voice features. Furthermore, the proposed approach not only includes an English one-shot multi-speaker TTS but also introduces a Korean one-shot multi-speaker TTS. We evaluate naturalness and speaker similarity of the generated speech using objective and subjective metrics. In the subjective evaluation, the proposed Korean one-shot multi-speaker TTS obtained naturalness mean opinion score (NMOS) of 3.36 and similarity MOS (SMOS) of 3.16. The objective evaluation of the proposed English and Korean one-shot multi-speaker TTS showed a prediction MOS (P-MOS) of 2.54 and 3.74, respectively. These results indicate that the performance of our proposed model is improved over the baseline models in terms of both naturalness and speaker similarity.

• The Journal of the Acoustical Society of Korea
• /
• v.20 no.8
• /
• pp.31-37
• /
• 2001

Following the recent trends of reducing the size of multimedia devices, we tried for the development of a compact-sized speaker to produce low-frequency sounds efficiently. For this work, equivalent-circuit analysis was used to get fundamental resonant frequency and then the structure of speaker components has been changed appropriately. As a result, an 80mm small-sized speaker was developed. The performance test showed that the resonant frequency of our system is 79 Hz while that of numerical analysis was 81Hz. At a distance of 1m from our speaker, the frequency ranges 80 Hz to 15kHz and the average sound pressure was found to be 84±2 dB. The second (at 400 Hz) and the third (at 100 Hz) high-frequency distortions of our system were 0.5% and 1.8% respectively, which is to be compared with the distortions of 0.9% and 6% in conventional speakers.