Definition
Tracheoesophageal Speech (TE Voice) is a method of speaking after a total laryngectomy. Air is redirected from the lungs through a tracheoesophageal puncture (TEP) into the esophagus, where vibrations are created and shaped into speech using the mouth and tongue. The resulting voice is functional, but it does not sound like the person’s original natural voice.
Relevance for Vocal Heirloom
Vocal Heirloom does not replace TE Voice and does not function as a daily communication tool.
Its purpose is different and emotional rather than medical:
• Many individuals facing laryngectomy never completed formal voice banking.
• Their pre-surgery recordings – home videos, voicemails, voice notes – are often the only remaining traces of their natural voice.
• Vocal Heirloom reconstructs that past personal voice to preserve identity or create meaningful moments for loved ones.
Aligned use cases include:
• Recording a wedding toast or message in one’s original voice.
• Creating a bedtime story or keepsake for children or grandchildren.
• Offering families a comforting, familiar voice that reflects warmth and personality.
This is not an assistive communication product.
Technical Background
• TE Voice is produced by esophageal vibration rather than vocal cords.
• It typically has limited pitch variation, reduced volume, and a rougher tone.
• TE Voice audio is not suitable for reconstructing a person’s original voice.
• Vocal Heirloom relies exclusively on recordings captured before the surgery.
• Audio Enhancement is used to clean old recordings prior to reconstruction.
Common Misunderstandings
• TE Voice does not replicate the speaker’s natural voice.
• Vocal Heirloom does not improve, modify, or replace TE Voice.
• TE Voice recordings cannot be used as input for AI voice reconstruction.
• Only pre-surgery recordings contain the vocal identity needed for restoration.
• The result is not a medical communication solution.
Factors That Influence Reconstruction Quality
• Availability of pre-surgery recordings with clear speech.
• Variation in vowels and consonants across clips.
• Lower background noise and lower compression (e.g., original video files).
• Emotional consistency, such as calm speech or natural laughter, enhances authenticity.
Typical Useful Sources for Pre-Surgery Voice
• Home videos captured on smartphones
• Saved voicemails from earlier years
• WhatsApp or iMessage voice notes
• Social media clips with spoken segments
• Any spontaneous recording with the person’s natural voice
Why It Matters for Identity and Memory
TE Voice serves as a functional communication method after surgery.
Vocal Heirloom serves a personal and emotional purpose:
• It preserves the original voice that represents identity and self-expression.
• It allows patients to create intentional messages or keepsakes in their natural voice.
• It provides families with a lasting, comforting connection to the person’s true sound.