Search Results for « Voice Conversion »

The history of Christianity in South India has always been an interesting theme for scholars across disciplines. Due to the peculiarity of the society, especially the caste system, Christianity has been conceived differently by the populace. The higher castes considered it as the religion of the ‘outcastes’, while Christianity was ‘liberating’ for the Dalits. Accordingly, mass movements happened in the Telugu-speaking Madras Presidency (or colonial Andhra Pradesh), and the depressed classes embraced the religion wholeheartedly. However, being influenced by the spirit of nationalism and an urge to liberate the country, the Christian converts decided to add ‘Indianness’ to Christianity. This led to the indigenization of the church and the establishment of the ‘Indian Church’. However, this process failed to cut the mustard in terms of liberation, and the Dalit converts ended up being ‘doubly marginalized’. In this light, this article will try to show how indigenization had pros and cons, especially the continuation of caste discrimination that plagued the church administration and the Dalits.

Kumar, S. (2019). Ambedkar’s journey of conversion to Buddhism. Contemporary Voice of Dalit . Advance online publication. Ahead of Print article withdrawn by publisher. Due to an administrative error, this article was accidentally published Online First and in Volume 11, Issue 2 with different DOIs. The correct and citable version of the article remains: Kumar, S. (2019). Ambedkar’s journey of conversion to Buddhism. Contemporary Voice of Dalit, 11 (2), 107–118. https://doi.org/10.1177/2455328X19825959

The history of religious conversions has highlighted two aspects. One is the transformation in one’s spiritual and transcendental realm and the other is the social and the political domain that encompasses a sense of rejection of existing religious and philosophical world views as well as assertion of one’s political outlook. In this context, this article explores the contours of one of the most important political thinkers of modern India, that is, B. R. Ambedkar who embraced Buddhism after 40 years of his experiment with the Hindu religion. This article is divided into two parts; the first deals with Ambedkar’s engagement with Hinduism with a hope of reforming the same but having failed in his attempt for 20 years, he declared to leave the religion in 1936. The second part deals with Ambedkar’s both explicit and implicit deliberations for selecting the right noble faith, that is, Buddhism whose foundation was egalitarianism, based on equality and compassion. He used Deweyian experimentalism and Buddhist rationalism, to reject Hinduism and seek refuge in the reformed Buddhism, that is, Navayana Buddhism.

We present an any-to-one voice conversion (VC) system, using an autoregressive model and LPCNet vocoder, aimed to enhance the converted speech in terms of naturalness, intelligibility, and speaker similarity. As the name implies, non-parallel any-to-one voice conversion does not require paired source and target speeches and can be employed for arbitrary speech conversion tasks. Recent advancements in neural-based vocoders, such as WaveNet, have improved the efficiency of speech synthesis. However, in practice, we find that the trajectory of some generated waveforms is not consistently smooth, leading to occasional voice errors. To address this issue, we propose to use an autoregressive (AR) conversion model along with the high-fidelity LPCNet vocoder. This combination not only solves the problems of waveform fluidity but also produces more natural and clear speech, with the added capability of real-time speech generation. To precisely represent the linguistic content of a given utterance, we use speaker-independent PPG features (SI-PPG) computed from an automatic speech recognition (ASR) model trained on a multi-speaker corpus. Next, a conversion model maps the SI-PPG to the acoustic representations used as input features for the LPCNet. The proposed autoregressive structure enables our system to produce the following prediction step outputs from the acoustic features predicted in the previous step. We evaluate the effectiveness of our system by performing any-to-one conversion pairs between native English speakers. Experimental results show that the proposed method outperforms state-of-the-art systems, producing higher speech quality and greater speaker similarity.

We present an any-to-one voice conversion (VC) system, using an autoregressive model and LPCNet vocoder, aimed to enhance the converted speech in terms of naturalness, intelligibility, and speaker similarity. As the name implies, non-parallel any-to-one voice conversion does not require paired source and target speeches and can be employed for arbitrary speech conversion tasks. Recent advancements in neural-based vocoders, such as WaveNet, have improved the efficiency of speech synthesis. However, in practice, we find that the trajectory of some generated waveforms is not consistently smooth, leading to occasional voice errors. To address this issue, we propose to use an autoregressive (AR) conversion model along with the high-fidelity LPCNet vocoder. This combination not only solves the problems of waveform fluidity but also produces more natural and clear speech, with the added capability of real-time speech generation. To precisely represent the linguistic content of a given utterance, we use speaker-independent PPG features (SI-PPG) computed from an automatic speech recognition (ASR) model trained on a multi-speaker corpus. Next, a conversion model maps the SI-PPG to the acoustic representations used as input features for the LPCNet. The proposed autoregressive structure enables our system to produce the following prediction step outputs from the acoustic features predicted in the previous step. We evaluate the effectiveness of our system by performing any-to-one conversion pairs between native English speakers. Experimental results show that the proposed method outperforms state-of-the-art systems, producing higher speech quality and greater speaker similarity.