ISCA Archive Interspeech 2024 Sessions Search Website Booklet
  ISCA Archive Sessions Search Website Booklet
×

Click on column names to sort.

Searching uses the 'and' of terms e.g. Smith Interspeech matches all papers by Smith in any Interspeech. The order of terms is not significant.

Use double quotes for exact phrasal matches e.g. "acoustic features".

Case is ignored.

Diacritics are optional e.g. lefevre also matches lefèvre (but not vice versa).

It can be useful to turn off spell-checking for the search box in your browser preferences.

If you prefer to scroll rather than page, increase the number in the show entries dropdown.

top

Interspeech 2024

Kos, Greece
1-5 September 2024

Chairs: Itshak Lapidot, Sharon Gannot
doi: 10.21437/Interspeech.2024
ISSN: 2958-1796

If you’re looking to create high-quality wiseguy (mobster-style) voiceovers using AI, here are the best tools and a short "essay" or script you can use to test them. 1. Top Tools for "Wiseguy" Voices

: It was a prominent voice on the GoAnimate platform until it was removed in 2016.

| Standard English | Wiseguy TTS Input | Why it works | | :--- | :--- | :--- | | Forget about it. | Fuggedaboutit. | Forces the slur and vowel merge. | | You’re joking, right? | Yous’ jokin’, right? | Adds the plural "yous" and drops the G. | | I need the money. | I need da money. | Replaces 'the' with a flap consonant. | | He is a dead man. | He’s a dead man. | Contraction plus hard stop. | | Listen to me. | Lissen ta me. | Drops the 'T' in listen and replaces 'to'. | text to speech wiseguy voice work

Applications: Where to Use Wiseguy TTS

The demand for this specific vocal style is exploding across several content verticals:

Example 2: "Listen, buddy, I'm gonna give you some advice. You wanna make it in this town? You gotta be tough, resourceful, and always on the lookout for a good score. Capisce?" Produce a ready-to-run SSML template for each example above

  • Produce a ready-to-run SSML template for each example above.
  • Draft a 1–2 hour recording script for custom wiseguy voice training.
  • Create a short checklist-based QA form for production reviews.

Fish Audio: You can use the Wiseguy (GoAnimate) (VoiceForge) AI Voice Generator on Fish Audio to generate instant speech. It supports adjustments for speed and pitch and is frequently used for character-driven stories.

Based on recent performance and user reviews, these platforms are the best for generating or cloning this specific voice: Fish Audio : You can use the Wiseguy

6.2 Typecasting and Stereotyping

Reliance on "Wiseguy" TTS relies on ethnic stereotypes. Overuse can be viewed as culturally insensitive, relying on caricatures of Italian-Americans. Brands and professional agencies generally avoid this style to prevent public relations backlash.

Search papers
Article

Text To Speech Wiseguy Voice Work !!better!! -

If you’re looking to create high-quality wiseguy (mobster-style) voiceovers using AI, here are the best tools and a short "essay" or script you can use to test them. 1. Top Tools for "Wiseguy" Voices

: It was a prominent voice on the GoAnimate platform until it was removed in 2016.

| Standard English | Wiseguy TTS Input | Why it works | | :--- | :--- | :--- | | Forget about it. | Fuggedaboutit. | Forces the slur and vowel merge. | | You’re joking, right? | Yous’ jokin’, right? | Adds the plural "yous" and drops the G. | | I need the money. | I need da money. | Replaces 'the' with a flap consonant. | | He is a dead man. | He’s a dead man. | Contraction plus hard stop. | | Listen to me. | Lissen ta me. | Drops the 'T' in listen and replaces 'to'. |

Applications: Where to Use Wiseguy TTS

The demand for this specific vocal style is exploding across several content verticals:

Example 2: "Listen, buddy, I'm gonna give you some advice. You wanna make it in this town? You gotta be tough, resourceful, and always on the lookout for a good score. Capisce?"

Fish Audio: You can use the Wiseguy (GoAnimate) (VoiceForge) AI Voice Generator on Fish Audio to generate instant speech. It supports adjustments for speed and pitch and is frequently used for character-driven stories.

Based on recent performance and user reviews, these platforms are the best for generating or cloning this specific voice:

6.2 Typecasting and Stereotyping

Reliance on "Wiseguy" TTS relies on ethnic stereotypes. Overuse can be viewed as culturally insensitive, relying on caricatures of Italian-Americans. Brands and professional agencies generally avoid this style to prevent public relations backlash.