Pune scientist leads global team helping ALS patients regain voice

Hindustan Times

9 hours ago

PUNE A Pune-based scientist is front and centre of a major milestone in neurotechnology – an implant-based brain-computer interface (BCI) that enables an individual with advanced amyotrophic lateral sclerosis (ALS) to speak in real time with natural intonation, and even sing. Pune-based scientist is part of neurotech project team that enables individual with advanced amyotrophic lateral sclerosis (ALS) to speak in real time with natural intonation, and even sing. (HT)
Dr Maitreyee Wairagkar – a former student of Jnana Prabodhini (Nigdi) and Fergusson College who completed her Engineering Masters and Ph.D. from the United Kingdom and is now based at UC Davis as 'project scientist' to lead the project since the last three years – has set an example of what Indian girls can achieve provided they get a chance.
Dr Wairagkar – working with her team of researchers at UC Davis's Neuroprosthetics Laboratory since the last three years – has led the project from conception to design to execution and developed this 'first-in-world' technology that demonstrates a brain-to-voice neuroprosthesis capable of synthesising speech with less than a 25-millisecond delay, virtually indistinguishable from natural vocal feedback. Dr Wairagkar is the first author on the study published in the scientific journal, 'Nature' on June 12, 2025.
Drawing on Dr Wairagkar's expertise, her team has developed algorithms to extract and denoise neural features, train phoneme and pitch decoders, and craft a full end-to-end voice synthesis system. Dr Wairagkar and team have enabled the decoding of fine-grained paralinguistic cues, allowing the user to express not just words but also emotion and melody.
The system uses 256 microscale electrodes implanted in the ventral precentral gyrus, which is the part of the brain crucial for speech production. In the course of the study, as the participant attempted to speak, neural signals were decoded in real time into phonemes and paralinguistic features like pitch and emphasis and subsequently transformed into audible speech through a vocoder and speaker system. Importantly, the participant was not only able to communicate new words but also ask questions, shift intonation, and sing simple melodies in a major leap towards expressive, spontaneous communication.
About the achievement, Dr Wairagkar said, 'What makes this technology extraordinary is not just that it translates brain activity into speech, but that it does so with the flow and character of natural voice. That expressiveness is what makes real conversation possible, and human.'
Dr Wairagkar's contributions allowed the participant to control tone and stress in real time; a feature absent in earlier BCIs that often relied on slow, word-by-word output.
Senior researchers at UC Davis, including Dr Sergey Stavisky and neurosurgeon Dr David Brandman, emphasised the emotional and practical impact of the work. 'This is the first time we have been able to restore a participant's own voice in real time, allowing him not only to talk but to sound like himself,' said Dr Stavisky.
Dr Brandman—who implanted the arrays under the BrainGate2 clinical trial—highlighted the emotional power of restoring not just speech, but the participant's own voice. Test listeners recognised nearly 60% of the words correctly when BCI-driven voice was used (compared to just 4% intelligibility in natural, dysarthric speech), underscoring dramatic improvements in communication clarity.
The neuroprosthesis not only decodes speech at the phoneme level but also captures prosody—how a sentence is said—making it the closest attempt yet at recreating natural, flowing conversation from thought alone. This milestone represents a profound shift in assistive communication for people living with ALS, brainstem strokes, or other forms of locked-in syndrome. It also puts India at the centre of a transformative global scientific collaboration through Dr Wairagkar's involvement.
The researchers note that although the findings are promising, brain-to-voice neuroprostheses remain in an early phase. A key limitation is that the research was performed with a single participant with ALS. It will be crucial to replicate these results with more participants, including those who have speech loss from other causes such as stroke. As further trials progress and the technology is refined, experts believe this innovation could redefine how neurotechnology restores voice and identity for millions who are otherwise left voiceless.